Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1994 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0280. Min Range: -5.0280
Max Act: 5.0280. Min Act: -0.1700
Data Index: 75289 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0280. Min Range: -5.0280
Max Act: 4.7780. Min Act: -0.1700
Data Index: 8449534 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0280. Min Range: -5.0280
Max Act: 4.7155. Min Act: -0.1700
Data Index: 8449533 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0280. Min Range: -5.0280
Max Act: 4.7155. Min Act: -0.1700
Data Index: 5171307 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0280. Min Range: -5.0280
Max Act: 4.6842. Min Act: -0.1700
Data Index: 8449536 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0280. Min Range: -5.0280
Max Act: 4.6530. Min Act: -0.1700
Data Index: 483768 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0280. Min Range: -5.0280
Max Act: 4.6530. Min Act: -0.1700
Data Index: 6137299 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0280. Min Range: -5.0280
Max Act: 4.6530. Min Act: -0.1700
Data Index: 8633375 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0280. Min Range: -5.0280
Max Act: 4.6217. Min Act: -0.1700
Data Index: 8479544 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0280. Min Range: -5.0280
Max Act: 4.6217. Min Act: -0.1700
Data Index: 4346453 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0280. Min Range: -5.0280
Max Act: 4.5905. Min Act: -0.1700
Data Index: 2294988 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0280. Min Range: -5.0280
Max Act: 4.5905. Min Act: -0.1700
Data Index: 5171306 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0280. Min Range: -5.0280
Max Act: 4.6217. Min Act: -0.1700
Data Index: 7487013 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0280. Min Range: -5.0280
Max Act: 4.5905. Min Act: -0.1700
Data Index: 3689283 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0280. Min Range: -5.0280
Max Act: 4.5592. Min Act: -0.1700
Data Index: 5412788 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0280. Min Range: -5.0280
Max Act: 4.5280. Min Act: -0.1700
Data Index: 3807985 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0280. Min Range: -5.0280
Max Act: 4.5592. Min Act: -0.1700
Data Index: 6365770 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0280. Min Range: -5.0280
Max Act: 4.5592. Min Act: -0.1700
Data Index: 4570777 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0280. Min Range: -5.0280
Max Act: 4.5280. Min Act: -0.1700
Data Index: 5775980 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0280. Min Range: -5.0280
Max Act: 4.5280. Min Act: -0.1700
Data Index: 4487170 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #19