Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4575 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2226. Min Range: -7.2226
Max Act: 7.2226. Min Act: -0.1700
Data Index: 7549472 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2226. Min Range: -7.2226
Max Act: 7.1601. Min Act: -0.1700
Data Index: 6343862 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2226. Min Range: -7.2226
Max Act: 7.0976. Min Act: -0.1700
Data Index: 7549464 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2226. Min Range: -7.2226
Max Act: 7.0976. Min Act: -0.1700
Data Index: 5951629 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2226. Min Range: -7.2226
Max Act: 7.0976. Min Act: -0.1700
Data Index: 899 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2226. Min Range: -7.2226
Max Act: 7.0351. Min Act: -0.1700
Data Index: 1629559 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2226. Min Range: -7.2226
Max Act: 7.0351. Min Act: -0.1700
Data Index: 7603877 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2226. Min Range: -7.2226
Max Act: 7.0351. Min Act: -0.1700
Data Index: 8001851 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2226. Min Range: -7.2226
Max Act: 7.0351. Min Act: -0.1700
Data Index: 6433404 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2226. Min Range: -7.2226
Max Act: 7.0351. Min Act: -0.1700
Data Index: 5472861 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2226. Min Range: -7.2226
Max Act: 7.0351. Min Act: -0.1700
Data Index: 280084 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2226. Min Range: -7.2226
Max Act: 7.0351. Min Act: -0.1700
Data Index: 6752023 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2226. Min Range: -7.2226
Max Act: 6.9726. Min Act: -0.1700
Data Index: 7549459 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2226. Min Range: -7.2226
Max Act: 6.9726. Min Act: -0.1700
Data Index: 7549460 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2226. Min Range: -7.2226
Max Act: 6.9726. Min Act: -0.1700
Data Index: 7549457 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2226. Min Range: -7.2226
Max Act: 6.9726. Min Act: -0.1700
Data Index: 7431377 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2226. Min Range: -7.2226
Max Act: 6.9726. Min Act: -0.1700
Data Index: 6689097 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2226. Min Range: -7.2226
Max Act: 6.9726. Min Act: -0.1700
Data Index: 3583268 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2226. Min Range: -7.2226
Max Act: 6.9726. Min Act: -0.1700
Data Index: 898 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2226. Min Range: -7.2226
Max Act: 6.9726. Min Act: -0.1700
Data Index: 168940 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #19