Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3037 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9671. Min Range: -5.9671
Max Act: 5.9671. Min Act: -0.1700
Data Index: 3503138 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9671. Min Range: -5.9671
Max Act: 5.9046. Min Act: -0.1700
Data Index: 6709381 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9671. Min Range: -5.9671
Max Act: 5.8733. Min Act: -0.1700
Data Index: 4996518 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9671. Min Range: -5.9671
Max Act: 5.8108. Min Act: -0.1700
Data Index: 3168553 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9671. Min Range: -5.9671
Max Act: 5.7483. Min Act: -0.1700
Data Index: 311158 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9671. Min Range: -5.9671
Max Act: 5.7171. Min Act: -0.1700
Data Index: 659751 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9671. Min Range: -5.9671
Max Act: 5.6858. Min Act: -0.1700
Data Index: 3742761 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9671. Min Range: -5.9671
Max Act: 5.6858. Min Act: -0.1700
Data Index: 456596 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9671. Min Range: -5.9671
Max Act: 5.6858. Min Act: -0.1700
Data Index: 8208474 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9671. Min Range: -5.9671
Max Act: 5.6546. Min Act: -0.1700
Data Index: 6756624 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9671. Min Range: -5.9671
Max Act: 5.6233. Min Act: -0.1700
Data Index: 4218021 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9671. Min Range: -5.9671
Max Act: 5.6233. Min Act: -0.1700
Data Index: 5639522 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9671. Min Range: -5.9671
Max Act: 5.5921. Min Act: -0.1700
Data Index: 556551 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9671. Min Range: -5.9671
Max Act: 5.5608. Min Act: -0.1700
Data Index: 8059645 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9671. Min Range: -5.9671
Max Act: 5.5296. Min Act: -0.1700
Data Index: 6505030 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9671. Min Range: -5.9671
Max Act: 5.5296. Min Act: -0.1700
Data Index: 4581500 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9671. Min Range: -5.9671
Max Act: 5.5296. Min Act: -0.1700
Data Index: 8716082 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9671. Min Range: -5.9671
Max Act: 5.5296. Min Act: -0.1700
Data Index: 3503137 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9671. Min Range: -5.9671
Max Act: 5.5296. Min Act: -0.1700
Data Index: 505422 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9671. Min Range: -5.9671
Max Act: 5.4983. Min Act: -0.1700
Data Index: 2799575 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #19