Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1984 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2210. Min Range: -7.2210
Max Act: 7.2210. Min Act: -0.1700
Data Index: 182407 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2210. Min Range: -7.2210
Max Act: 6.9085. Min Act: -0.1700
Data Index: 517734 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2210. Min Range: -7.2210
Max Act: 6.5960. Min Act: -0.1700
Data Index: 8405343 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2210. Min Range: -7.2210
Max Act: 6.5648. Min Act: -0.1700
Data Index: 4012659 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2210. Min Range: -7.2210
Max Act: 6.5335. Min Act: -0.1700
Data Index: 4698222 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2210. Min Range: -7.2210
Max Act: 6.3773. Min Act: -0.1700
Data Index: 6402820 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2210. Min Range: -7.2210
Max Act: 6.3773. Min Act: -0.1700
Data Index: 2683459 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2210. Min Range: -7.2210
Max Act: 6.3773. Min Act: -0.1700
Data Index: 230045 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2210. Min Range: -7.2210
Max Act: 6.3148. Min Act: -0.1700
Data Index: 4292161 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2210. Min Range: -7.2210
Max Act: 6.2523. Min Act: -0.1700
Data Index: 1501403 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2210. Min Range: -7.2210
Max Act: 6.2523. Min Act: -0.1700
Data Index: 6107547 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2210. Min Range: -7.2210
Max Act: 6.1898. Min Act: -0.1700
Data Index: 171596 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2210. Min Range: -7.2210
Max Act: 6.1898. Min Act: -0.1700
Data Index: 4450176 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2210. Min Range: -7.2210
Max Act: 6.1585. Min Act: -0.1700
Data Index: 7454766 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2210. Min Range: -7.2210
Max Act: 6.1585. Min Act: -0.1700
Data Index: 8107777 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2210. Min Range: -7.2210
Max Act: 6.1585. Min Act: -0.1700
Data Index: 2098293 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2210. Min Range: -7.2210
Max Act: 6.1585. Min Act: -0.1700
Data Index: 7204486 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2210. Min Range: -7.2210
Max Act: 6.1273. Min Act: -0.1700
Data Index: 140010 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2210. Min Range: -7.2210
Max Act: 6.1585. Min Act: -0.1700
Data Index: 2983595 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2210. Min Range: -7.2210
Max Act: 6.0960. Min Act: -0.1700
Data Index: 5931016 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #19