Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4899 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7468. Min Range: -3.7468
Max Act: 3.7468. Min Act: -0.1700
Data Index: 4517671 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7468. Min Range: -3.7468
Max Act: 3.6842. Min Act: -0.1700
Data Index: 3651805 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7468. Min Range: -3.7468
Max Act: 3.5903. Min Act: -0.1700
Data Index: 8304863 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7468. Min Range: -3.7468
Max Act: 3.6216. Min Act: -0.1700
Data Index: 7031665 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7468. Min Range: -3.7468
Max Act: 3.5903. Min Act: -0.1700
Data Index: 2946924 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7468. Min Range: -3.7468
Max Act: 3.5903. Min Act: -0.1700
Data Index: 8287073 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7468. Min Range: -3.7468
Max Act: 3.5590. Min Act: -0.1700
Data Index: 8425495 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7468. Min Range: -3.7468
Max Act: 3.5277. Min Act: -0.1700
Data Index: 8168228 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7468. Min Range: -3.7468
Max Act: 3.5277. Min Act: -0.1700
Data Index: 3926138 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7468. Min Range: -3.7468
Max Act: 3.5277. Min Act: -0.1700
Data Index: 6951068 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7468. Min Range: -3.7468
Max Act: 3.4964. Min Act: -0.1700
Data Index: 1191365 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7468. Min Range: -3.7468
Max Act: 3.4807. Min Act: -0.1700
Data Index: 8416529 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7468. Min Range: -3.7468
Max Act: 3.4807. Min Act: -0.1700
Data Index: 656185 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7468. Min Range: -3.7468
Max Act: 3.4651. Min Act: -0.1700
Data Index: 3379483 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7468. Min Range: -3.7468
Max Act: 3.4651. Min Act: -0.1700
Data Index: 6373577 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7468. Min Range: -3.7468
Max Act: 3.4651. Min Act: -0.1700
Data Index: 6951067 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7468. Min Range: -3.7468
Max Act: 3.4337. Min Act: -0.1700
Data Index: 512809 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7468. Min Range: -3.7468
Max Act: 3.4337. Min Act: -0.1700
Data Index: 8080056 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7468. Min Range: -3.7468
Max Act: 3.4337. Min Act: -0.1700
Data Index: 8714484 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7468. Min Range: -3.7468
Max Act: 3.4181. Min Act: -0.1700
Data Index: 3084413 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #19