Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 480 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7761. Min Range: -6.7761
Max Act: 6.7761. Min Act: -0.1700
Data Index: 2083755 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7761. Min Range: -6.7761
Max Act: 6.6823. Min Act: -0.1700
Data Index: 6117023 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7761. Min Range: -6.7761
Max Act: 6.6511. Min Act: -0.1700
Data Index: 7240126 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7761. Min Range: -6.7761
Max Act: 6.6198. Min Act: -0.1700
Data Index: 4299680 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7761. Min Range: -6.7761
Max Act: 6.6198. Min Act: -0.1700
Data Index: 3506289 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7761. Min Range: -6.7761
Max Act: 6.5573. Min Act: -0.1700
Data Index: 2244427 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7761. Min Range: -6.7761
Max Act: 6.5573. Min Act: -0.1700
Data Index: 6742292 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7761. Min Range: -6.7761
Max Act: 6.5261. Min Act: -0.1700
Data Index: 2726588 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7761. Min Range: -6.7761
Max Act: 6.5261. Min Act: -0.1700
Data Index: 5912780 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7761. Min Range: -6.7761
Max Act: 6.5261. Min Act: -0.1700
Data Index: 2362127 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7761. Min Range: -6.7761
Max Act: 6.4948. Min Act: -0.1700
Data Index: 6587812 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7761. Min Range: -6.7761
Max Act: 6.4323. Min Act: -0.1700
Data Index: 2034452 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7761. Min Range: -6.7761
Max Act: 6.4323. Min Act: -0.1700
Data Index: 227367 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7761. Min Range: -6.7761
Max Act: 6.3698. Min Act: -0.1700
Data Index: 494655 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7761. Min Range: -6.7761
Max Act: 6.4011. Min Act: -0.1700
Data Index: 4828203 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7761. Min Range: -6.7761
Max Act: 6.4323. Min Act: -0.1700
Data Index: 5583427 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7761. Min Range: -6.7761
Max Act: 6.4011. Min Act: -0.1700
Data Index: 5269942 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7761. Min Range: -6.7761
Max Act: 6.4011. Min Act: -0.1700
Data Index: 3679201 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7761. Min Range: -6.7761
Max Act: 6.4011. Min Act: -0.1700
Data Index: 821811 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7761. Min Range: -6.7761
Max Act: 6.4011. Min Act: -0.1700
Data Index: 6071313 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #19