Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4196 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4202. Min Range: -4.4202
Max Act: 4.4202. Min Act: -0.1700
Data Index: 982584 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4202. Min Range: -4.4202
Max Act: 4.2327. Min Act: -0.1700
Data Index: 6746602 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4202. Min Range: -4.4202
Max Act: 4.1077. Min Act: -0.1699
Data Index: 117464 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4202. Min Range: -4.4202
Max Act: 4.1390. Min Act: -0.1700
Data Index: 1529060 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4202. Min Range: -4.4202
Max Act: 4.1390. Min Act: -0.1700
Data Index: 524973 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4202. Min Range: -4.4202
Max Act: 4.1077. Min Act: -0.1700
Data Index: 580027 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4202. Min Range: -4.4202
Max Act: 4.1077. Min Act: -0.1700
Data Index: 3791951 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4202. Min Range: -4.4202
Max Act: 4.0765. Min Act: -0.1700
Data Index: 7841333 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4202. Min Range: -4.4202
Max Act: 4.0765. Min Act: -0.1700
Data Index: 7672230 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4202. Min Range: -4.4202
Max Act: 4.0765. Min Act: -0.1700
Data Index: 2825144 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4202. Min Range: -4.4202
Max Act: 4.0765. Min Act: -0.1700
Data Index: 3162512 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4202. Min Range: -4.4202
Max Act: 4.0452. Min Act: -0.1700
Data Index: 5197417 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4202. Min Range: -4.4202
Max Act: 4.0452. Min Act: -0.1700
Data Index: 4408455 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4202. Min Range: -4.4202
Max Act: 4.0765. Min Act: -0.1700
Data Index: 6790360 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4202. Min Range: -4.4202
Max Act: 4.0452. Min Act: -0.1699
Data Index: 3172812 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4202. Min Range: -4.4202
Max Act: 4.0452. Min Act: -0.1700
Data Index: 7585219 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4202. Min Range: -4.4202
Max Act: 3.9827. Min Act: -0.1700
Data Index: 2559260 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4202. Min Range: -4.4202
Max Act: 3.9827. Min Act: -0.1700
Data Index: 5865539 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4202. Min Range: -4.4202
Max Act: 4.0139. Min Act: -0.1700
Data Index: 6605380 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4202. Min Range: -4.4202
Max Act: 4.0139. Min Act: -0.1700
Data Index: 7068990 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #19