Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4932 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3195. Min Range: -4.3195
Max Act: 4.3195. Min Act: -0.1677
Data Index: 485007 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3195. Min Range: -4.3195
Max Act: 4.2257. Min Act: -0.1700
Data Index: 7327000 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3195. Min Range: -4.3195
Max Act: 4.2257. Min Act: -0.1700
Data Index: 7198768 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3195. Min Range: -4.3195
Max Act: 4.1944. Min Act: -0.1700
Data Index: 8758937 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3195. Min Range: -4.3195
Max Act: 4.1632. Min Act: -0.1700
Data Index: 3528915 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3195. Min Range: -4.3195
Max Act: 4.1944. Min Act: -0.1700
Data Index: 2420338 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3195. Min Range: -4.3195
Max Act: 4.1632. Min Act: -0.1700
Data Index: 5697719 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3195. Min Range: -4.3195
Max Act: 4.1319. Min Act: -0.1700
Data Index: 4884244 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3195. Min Range: -4.3195
Max Act: 4.1007. Min Act: -0.1700
Data Index: 3666043 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3195. Min Range: -4.3195
Max Act: 4.1007. Min Act: -0.1700
Data Index: 4073759 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3195. Min Range: -4.3195
Max Act: 4.1007. Min Act: -0.1700
Data Index: 2502339 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3195. Min Range: -4.3195
Max Act: 4.1007. Min Act: -0.1700
Data Index: 2308271 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3195. Min Range: -4.3195
Max Act: 4.0694. Min Act: -0.1700
Data Index: 5686604 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3195. Min Range: -4.3195
Max Act: 4.0694. Min Act: -0.1700
Data Index: 7639278 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3195. Min Range: -4.3195
Max Act: 4.0694. Min Act: -0.1700
Data Index: 665606 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3195. Min Range: -4.3195
Max Act: 4.0694. Min Act: -0.1700
Data Index: 3601420 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3195. Min Range: -4.3195
Max Act: 4.0382. Min Act: -0.1700
Data Index: 5076382 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3195. Min Range: -4.3195
Max Act: 4.0382. Min Act: -0.1700
Data Index: 4951651 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3195. Min Range: -4.3195
Max Act: 4.0694. Min Act: -0.1700
Data Index: 1151398 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3195. Min Range: -4.3195
Max Act: 4.0382. Min Act: -0.1700
Data Index: 1378512 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19