Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1127 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9086. Min Range: -3.9086
Max Act: 3.9086. Min Act: -0.1700
Data Index: 4095551 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9086. Min Range: -3.9086
Max Act: 3.8148. Min Act: -0.1700
Data Index: 856242 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9086. Min Range: -3.9086
Max Act: 3.6271. Min Act: -0.1700
Data Index: 1851353 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9086. Min Range: -3.9086
Max Act: 3.5958. Min Act: -0.1700
Data Index: 856238 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9086. Min Range: -3.9086
Max Act: 3.6271. Min Act: -0.1700
Data Index: 5996035 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9086. Min Range: -3.9086
Max Act: 3.5802. Min Act: -0.1700
Data Index: 7157131 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9086. Min Range: -3.9086
Max Act: 3.5645. Min Act: -0.1700
Data Index: 6637253 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9086. Min Range: -3.9086
Max Act: 3.5489. Min Act: -0.1700
Data Index: 8732229 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9086. Min Range: -3.9086
Max Act: 3.5489. Min Act: -0.1700
Data Index: 5941332 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9086. Min Range: -3.9086
Max Act: 3.5332. Min Act: -0.1700
Data Index: 7710924 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9086. Min Range: -3.9086
Max Act: 3.5175. Min Act: -0.1700
Data Index: 7157130 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9086. Min Range: -3.9086
Max Act: 3.5175. Min Act: -0.1700
Data Index: 122029 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9086. Min Range: -3.9086
Max Act: 3.5175. Min Act: -0.1700
Data Index: 6275703 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9086. Min Range: -3.9086
Max Act: 3.5175. Min Act: -0.1700
Data Index: 7770830 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9086. Min Range: -3.9086
Max Act: 3.4862. Min Act: -0.1700
Data Index: 122034 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9086. Min Range: -3.9086
Max Act: 3.4862. Min Act: -0.1700
Data Index: 122026 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9086. Min Range: -3.9086
Max Act: 3.4706. Min Act: -0.1700
Data Index: 8759573 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9086. Min Range: -3.9086
Max Act: 3.4549. Min Act: -0.1700
Data Index: 2043960 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9086. Min Range: -3.9086
Max Act: 3.4549. Min Act: -0.1700
Data Index: 4428714 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9086. Min Range: -3.9086
Max Act: 3.4392. Min Act: -0.1700
Data Index: 8319580 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #19