Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4320 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.5585. Min Range: -10.5585
Max Act: 10.5585. Min Act: -0.1700
Data Index: 7388496 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.5585. Min Range: -10.5585
Max Act: 10.4960. Min Act: -0.1700
Data Index: 5580609 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.5585. Min Range: -10.5585
Max Act: 10.3710. Min Act: -0.1700
Data Index: 7415834 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.5585. Min Range: -10.5585
Max Act: 10.3085. Min Act: -0.1700
Data Index: 6723512 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.5585. Min Range: -10.5585
Max Act: 10.2460. Min Act: -0.1700
Data Index: 1989397 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.5585. Min Range: -10.5585
Max Act: 10.1210. Min Act: -0.1700
Data Index: 4687821 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.5585. Min Range: -10.5585
Max Act: 10.1210. Min Act: -0.1700
Data Index: 6058333 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.5585. Min Range: -10.5585
Max Act: 10.0585. Min Act: -0.1700
Data Index: 3017397 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.5585. Min Range: -10.5585
Max Act: 10.0585. Min Act: -0.1700
Data Index: 3386231 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.5585. Min Range: -10.5585
Max Act: 10.1210. Min Act: -0.1700
Data Index: 6344803 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.5585. Min Range: -10.5585
Max Act: 10.0585. Min Act: -0.1700
Data Index: 5809764 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.5585. Min Range: -10.5585
Max Act: 9.9335. Min Act: -0.1700
Data Index: 5564947 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.5585. Min Range: -10.5585
Max Act: 9.9960. Min Act: -0.1700
Data Index: 5881920 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.5585. Min Range: -10.5585
Max Act: 9.9960. Min Act: -0.1700
Data Index: 1184233 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.5585. Min Range: -10.5585
Max Act: 9.9960. Min Act: -0.1700
Data Index: 33345 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.5585. Min Range: -10.5585
Max Act: 9.9960. Min Act: -0.1700
Data Index: 5663127 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.5585. Min Range: -10.5585
Max Act: 9.9960. Min Act: -0.1700
Data Index: 2607648 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.5585. Min Range: -10.5585
Max Act: 9.9960. Min Act: -0.1700
Data Index: 7133012 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.5585. Min Range: -10.5585
Max Act: 9.9335. Min Act: -0.1700
Data Index: 6091963 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.5585. Min Range: -10.5585
Max Act: 9.9335. Min Act: -0.1700
Data Index: 3966291 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #19