Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3006 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7493. Min Range: -9.7493
Max Act: 9.7493. Min Act: -0.1700
Data Index: 5852702 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7493. Min Range: -9.7493
Max Act: 9.4368. Min Act: -0.1700
Data Index: 8784299 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7493. Min Range: -9.7493
Max Act: 9.4993. Min Act: -0.1700
Data Index: 3188878 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7493. Min Range: -9.7493
Max Act: 9.1868. Min Act: -0.1700
Data Index: 1243554 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7493. Min Range: -9.7493
Max Act: 9.1243. Min Act: -0.1700
Data Index: 3328682 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7493. Min Range: -9.7493
Max Act: 9.0618. Min Act: -0.1700
Data Index: 7727745 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7493. Min Range: -9.7493
Max Act: 8.9993. Min Act: -0.1700
Data Index: 6541920 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7493. Min Range: -9.7493
Max Act: 8.9368. Min Act: -0.1700
Data Index: 8744502 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7493. Min Range: -9.7493
Max Act: 8.9368. Min Act: -0.1700
Data Index: 362515 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7493. Min Range: -9.7493
Max Act: 8.8743. Min Act: -0.1700
Data Index: 7394274 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7493. Min Range: -9.7493
Max Act: 8.8743. Min Act: -0.1700
Data Index: 6339310 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7493. Min Range: -9.7493
Max Act: 8.8743. Min Act: -0.1700
Data Index: 6785242 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7493. Min Range: -9.7493
Max Act: 8.8743. Min Act: -0.1700
Data Index: 4005924 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7493. Min Range: -9.7493
Max Act: 8.7493. Min Act: -0.1700
Data Index: 5666956 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7493. Min Range: -9.7493
Max Act: 8.8118. Min Act: -0.1700
Data Index: 4985895 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7493. Min Range: -9.7493
Max Act: 8.8118. Min Act: -0.1700
Data Index: 4650484 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7493. Min Range: -9.7493
Max Act: 8.7493. Min Act: -0.1700
Data Index: 7772051 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7493. Min Range: -9.7493
Max Act: 8.7493. Min Act: -0.1700
Data Index: 8228182 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7493. Min Range: -9.7493
Max Act: 8.7493. Min Act: -0.1700
Data Index: 1021236 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7493. Min Range: -9.7493
Max Act: 8.7493. Min Act: -0.1700
Data Index: 1813435 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #19