Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 117 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2881. Min Range: -7.2881
Max Act: 7.2881. Min Act: -0.1700
Data Index: 7495839 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2881. Min Range: -7.2881
Max Act: 7.1631. Min Act: -0.1700
Data Index: 7294342 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2881. Min Range: -7.2881
Max Act: 7.0693. Min Act: -0.1700
Data Index: 1032724 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2881. Min Range: -7.2881
Max Act: 6.9756. Min Act: -0.1700
Data Index: 5077 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2881. Min Range: -7.2881
Max Act: 6.9443. Min Act: -0.1700
Data Index: 7287167 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2881. Min Range: -7.2881
Max Act: 6.9443. Min Act: -0.1700
Data Index: 585541 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2881. Min Range: -7.2881
Max Act: 6.9131. Min Act: -0.1700
Data Index: 2084298 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2881. Min Range: -7.2881
Max Act: 6.8818. Min Act: -0.1700
Data Index: 1520482 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2881. Min Range: -7.2881
Max Act: 6.8506. Min Act: -0.1700
Data Index: 6239805 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2881. Min Range: -7.2881
Max Act: 6.8506. Min Act: -0.1700
Data Index: 5039790 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2881. Min Range: -7.2881
Max Act: 6.8193. Min Act: -0.1700
Data Index: 4137581 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2881. Min Range: -7.2881
Max Act: 6.8193. Min Act: -0.1700
Data Index: 167791 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2881. Min Range: -7.2881
Max Act: 6.7881. Min Act: -0.1700
Data Index: 5274896 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2881. Min Range: -7.2881
Max Act: 6.7568. Min Act: -0.1700
Data Index: 8040575 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2881. Min Range: -7.2881
Max Act: 6.7568. Min Act: -0.1700
Data Index: 6994770 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2881. Min Range: -7.2881
Max Act: 6.7568. Min Act: -0.1700
Data Index: 2198441 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2881. Min Range: -7.2881
Max Act: 6.7568. Min Act: -0.1700
Data Index: 8334490 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2881. Min Range: -7.2881
Max Act: 6.7256. Min Act: -0.1700
Data Index: 7990132 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2881. Min Range: -7.2881
Max Act: 6.7568. Min Act: -0.1700
Data Index: 595974 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2881. Min Range: -7.2881
Max Act: 6.6943. Min Act: -0.1700
Data Index: 3668215 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #19