Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1904 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3354. Min Range: -6.3354
Max Act: 6.3354. Min Act: -0.1700
Data Index: 1611132 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3354. Min Range: -6.3354
Max Act: 6.1791. Min Act: -0.1700
Data Index: 5518694 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3354. Min Range: -6.3354
Max Act: 6.0229. Min Act: -0.1700
Data Index: 2922889 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3354. Min Range: -6.3354
Max Act: 5.9916. Min Act: -0.1700
Data Index: 1642388 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3354. Min Range: -6.3354
Max Act: 5.9916. Min Act: -0.1700
Data Index: 6879977 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3354. Min Range: -6.3354
Max Act: 5.9916. Min Act: -0.1700
Data Index: 7133702 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3354. Min Range: -6.3354
Max Act: 5.9604. Min Act: -0.1700
Data Index: 6763990 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3354. Min Range: -6.3354
Max Act: 5.9604. Min Act: -0.1700
Data Index: 8444768 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3354. Min Range: -6.3354
Max Act: 5.9604. Min Act: -0.1700
Data Index: 7126172 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3354. Min Range: -6.3354
Max Act: 5.9291. Min Act: -0.1700
Data Index: 3589524 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3354. Min Range: -6.3354
Max Act: 5.9291. Min Act: -0.1700
Data Index: 8442162 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3354. Min Range: -6.3354
Max Act: 5.9291. Min Act: -0.1700
Data Index: 8605922 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3354. Min Range: -6.3354
Max Act: 5.8979. Min Act: -0.1700
Data Index: 7590326 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3354. Min Range: -6.3354
Max Act: 5.8979. Min Act: -0.1700
Data Index: 3382321 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3354. Min Range: -6.3354
Max Act: 5.8666. Min Act: -0.1700
Data Index: 8003536 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3354. Min Range: -6.3354
Max Act: 5.8666. Min Act: -0.1700
Data Index: 2749835 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3354. Min Range: -6.3354
Max Act: 5.8666. Min Act: -0.1700
Data Index: 7174748 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3354. Min Range: -6.3354
Max Act: 5.8666. Min Act: -0.1700
Data Index: 4987097 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3354. Min Range: -6.3354
Max Act: 5.8666. Min Act: -0.1700
Data Index: 701808 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3354. Min Range: -6.3354
Max Act: 5.8666. Min Act: -0.1700
Data Index: 8575783 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #19