Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3780 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9994. Min Range: -5.9994
Max Act: 5.9994. Min Act: -0.1700
Data Index: 6884347 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9994. Min Range: -5.9994
Max Act: 5.9681. Min Act: -0.1700
Data Index: 6079205 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9994. Min Range: -5.9994
Max Act: 5.9681. Min Act: -0.1700
Data Index: 8600780 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9994. Min Range: -5.9994
Max Act: 5.9056. Min Act: -0.1700
Data Index: 8377453 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9994. Min Range: -5.9994
Max Act: 5.8119. Min Act: -0.1700
Data Index: 5406575 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9994. Min Range: -5.9994
Max Act: 5.8119. Min Act: -0.1700
Data Index: 6959257 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9994. Min Range: -5.9994
Max Act: 5.7494. Min Act: -0.1700
Data Index: 7052256 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9994. Min Range: -5.9994
Max Act: 5.7494. Min Act: -0.1700
Data Index: 2574703 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9994. Min Range: -5.9994
Max Act: 5.6869. Min Act: -0.1700
Data Index: 1833663 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9994. Min Range: -5.9994
Max Act: 5.6244. Min Act: -0.1700
Data Index: 452207 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9994. Min Range: -5.9994
Max Act: 5.6244. Min Act: -0.1700
Data Index: 1741443 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9994. Min Range: -5.9994
Max Act: 5.5931. Min Act: -0.1700
Data Index: 5573251 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9994. Min Range: -5.9994
Max Act: 5.5931. Min Act: -0.1700
Data Index: 7547137 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9994. Min Range: -5.9994
Max Act: 5.6244. Min Act: -0.1700
Data Index: 5543495 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9994. Min Range: -5.9994
Max Act: 5.5619. Min Act: -0.1700
Data Index: 2021439 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9994. Min Range: -5.9994
Max Act: 5.5619. Min Act: -0.1700
Data Index: 5356319 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9994. Min Range: -5.9994
Max Act: 5.5619. Min Act: -0.1700
Data Index: 2672146 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9994. Min Range: -5.9994
Max Act: 5.5306. Min Act: -0.1700
Data Index: 6919233 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9994. Min Range: -5.9994
Max Act: 5.5306. Min Act: -0.1700
Data Index: 4896576 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9994. Min Range: -5.9994
Max Act: 5.4994. Min Act: -0.1700
Data Index: 5806937 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #19