Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2415 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.1273. Min Range: -11.1273
Max Act: 11.1273. Min Act: -0.1700
Data Index: 2175575 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.1273. Min Range: -11.1273
Max Act: 10.7523. Min Act: -0.1700
Data Index: 7893238 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.1273. Min Range: -11.1273
Max Act: 10.6273. Min Act: -0.1700
Data Index: 2463100 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.1273. Min Range: -11.1273
Max Act: 10.5648. Min Act: -0.1700
Data Index: 1743636 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.1273. Min Range: -11.1273
Max Act: 10.5023. Min Act: -0.1700
Data Index: 6304670 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.1273. Min Range: -11.1273
Max Act: 10.5023. Min Act: -0.1700
Data Index: 3392528 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.1273. Min Range: -11.1273
Max Act: 10.4398. Min Act: -0.1700
Data Index: 891342 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.1273. Min Range: -11.1273
Max Act: 10.3773. Min Act: -0.1700
Data Index: 6870778 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.1273. Min Range: -11.1273
Max Act: 10.3148. Min Act: -0.1700
Data Index: 3671549 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.1273. Min Range: -11.1273
Max Act: 10.3773. Min Act: -0.1700
Data Index: 7979176 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.1273. Min Range: -11.1273
Max Act: 10.1898. Min Act: -0.1700
Data Index: 6950772 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.1273. Min Range: -11.1273
Max Act: 10.1273. Min Act: -0.1700
Data Index: 2285089 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.1273. Min Range: -11.1273
Max Act: 10.1273. Min Act: -0.1700
Data Index: 6019161 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.1273. Min Range: -11.1273
Max Act: 10.0648. Min Act: -0.1700
Data Index: 7825712 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.1273. Min Range: -11.1273
Max Act: 10.0648. Min Act: -0.1700
Data Index: 3652632 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.1273. Min Range: -11.1273
Max Act: 10.0648. Min Act: -0.1700
Data Index: 3185030 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.1273. Min Range: -11.1273
Max Act: 10.0023. Min Act: -0.1700
Data Index: 4563414 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.1273. Min Range: -11.1273
Max Act: 10.0023. Min Act: -0.1700
Data Index: 3444684 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.1273. Min Range: -11.1273
Max Act: 10.0023. Min Act: -0.1700
Data Index: 7416095 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.1273. Min Range: -11.1273
Max Act: 10.0023. Min Act: -0.1700
Data Index: 3006903 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #19