Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2877 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1366. Min Range: -6.1366
Max Act: 6.1366. Min Act: -0.1700
Data Index: 3344091 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1366. Min Range: -6.1366
Max Act: 5.9804. Min Act: -0.1700
Data Index: 4557657 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1366. Min Range: -6.1366
Max Act: 5.9491. Min Act: -0.1700
Data Index: 7941449 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1366. Min Range: -6.1366
Max Act: 5.9491. Min Act: -0.1700
Data Index: 8609933 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1366. Min Range: -6.1366
Max Act: 5.9491. Min Act: -0.1700
Data Index: 624399 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1366. Min Range: -6.1366
Max Act: 5.8866. Min Act: -0.1700
Data Index: 4622636 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1366. Min Range: -6.1366
Max Act: 5.8554. Min Act: -0.1700
Data Index: 8467652 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1366. Min Range: -6.1366
Max Act: 5.7304. Min Act: -0.1700
Data Index: 4959073 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1366. Min Range: -6.1366
Max Act: 5.7304. Min Act: -0.1700
Data Index: 370689 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1366. Min Range: -6.1366
Max Act: 5.6991. Min Act: -0.1700
Data Index: 7731123 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1366. Min Range: -6.1366
Max Act: 5.6991. Min Act: -0.1700
Data Index: 5354515 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1366. Min Range: -6.1366
Max Act: 5.6679. Min Act: -0.1700
Data Index: 3428639 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1366. Min Range: -6.1366
Max Act: 5.6679. Min Act: -0.1700
Data Index: 3450127 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1366. Min Range: -6.1366
Max Act: 5.6679. Min Act: -0.1700
Data Index: 2301620 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1366. Min Range: -6.1366
Max Act: 5.6679. Min Act: -0.1700
Data Index: 5109897 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1366. Min Range: -6.1366
Max Act: 5.6679. Min Act: -0.1700
Data Index: 2894829 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1366. Min Range: -6.1366
Max Act: 5.6679. Min Act: -0.1700
Data Index: 326852 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1366. Min Range: -6.1366
Max Act: 5.6366. Min Act: -0.1700
Data Index: 6306090 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1366. Min Range: -6.1366
Max Act: 5.6366. Min Act: -0.1700
Data Index: 3546248 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1366. Min Range: -6.1366
Max Act: 5.6366. Min Act: -0.1700
Data Index: 1231225 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #19