Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4934 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0084. Min Range: -7.0084
Max Act: 7.0084. Min Act: -0.1700
Data Index: 7042503 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0084. Min Range: -7.0084
Max Act: 6.7584. Min Act: -0.1700
Data Index: 8451836 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0084. Min Range: -7.0084
Max Act: 6.7584. Min Act: -0.1700
Data Index: 2565025 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0084. Min Range: -7.0084
Max Act: 6.6334. Min Act: -0.1700
Data Index: 6265977 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0084. Min Range: -7.0084
Max Act: 6.5709. Min Act: -0.1700
Data Index: 382891 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0084. Min Range: -7.0084
Max Act: 6.5396. Min Act: -0.1700
Data Index: 6632980 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0084. Min Range: -7.0084
Max Act: 6.5084. Min Act: -0.1700
Data Index: 5510237 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0084. Min Range: -7.0084
Max Act: 6.5396. Min Act: -0.1700
Data Index: 8600325 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0084. Min Range: -7.0084
Max Act: 6.5396. Min Act: -0.1700
Data Index: 6291863 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0084. Min Range: -7.0084
Max Act: 6.5084. Min Act: -0.1700
Data Index: 7923825 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0084. Min Range: -7.0084
Max Act: 6.4146. Min Act: -0.1700
Data Index: 2144332 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0084. Min Range: -7.0084
Max Act: 6.4146. Min Act: -0.1700
Data Index: 4138771 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0084. Min Range: -7.0084
Max Act: 6.3834. Min Act: -0.1700
Data Index: 6431762 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0084. Min Range: -7.0084
Max Act: 6.3521. Min Act: -0.1700
Data Index: 1897051 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0084. Min Range: -7.0084
Max Act: 6.3521. Min Act: -0.1700
Data Index: 3619409 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0084. Min Range: -7.0084
Max Act: 6.3521. Min Act: -0.1700
Data Index: 7055520 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0084. Min Range: -7.0084
Max Act: 6.3521. Min Act: -0.1700
Data Index: 7577214 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0084. Min Range: -7.0084
Max Act: 6.3521. Min Act: -0.1700
Data Index: 2751146 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0084. Min Range: -7.0084
Max Act: 6.3209. Min Act: -0.1700
Data Index: 8111381 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0084. Min Range: -7.0084
Max Act: 6.3209. Min Act: -0.1700
Data Index: 2294575 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #19