Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1678 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7193. Min Range: -6.7193
Max Act: 6.7193. Min Act: -0.1700
Data Index: 2662923 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7193. Min Range: -6.7193
Max Act: 6.6881. Min Act: -0.1700
Data Index: 7300516 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7193. Min Range: -6.7193
Max Act: 6.6881. Min Act: -0.1700
Data Index: 526137 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7193. Min Range: -6.7193
Max Act: 6.6568. Min Act: -0.1700
Data Index: 3089257 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7193. Min Range: -6.7193
Max Act: 6.6256. Min Act: -0.1700
Data Index: 7273094 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7193. Min Range: -6.7193
Max Act: 6.6256. Min Act: -0.1700
Data Index: 5640724 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7193. Min Range: -6.7193
Max Act: 6.5631. Min Act: -0.1700
Data Index: 3470049 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7193. Min Range: -6.7193
Max Act: 6.5631. Min Act: -0.1700
Data Index: 5216956 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7193. Min Range: -6.7193
Max Act: 6.5318. Min Act: -0.1700
Data Index: 6065037 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7193. Min Range: -6.7193
Max Act: 6.5318. Min Act: -0.1700
Data Index: 4989519 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7193. Min Range: -6.7193
Max Act: 6.5006. Min Act: -0.1700
Data Index: 8774483 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7193. Min Range: -6.7193
Max Act: 6.4693. Min Act: -0.1700
Data Index: 3332691 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7193. Min Range: -6.7193
Max Act: 6.4693. Min Act: -0.1700
Data Index: 7954449 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7193. Min Range: -6.7193
Max Act: 6.4381. Min Act: -0.1700
Data Index: 4938818 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7193. Min Range: -6.7193
Max Act: 6.4693. Min Act: -0.1700
Data Index: 286425 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7193. Min Range: -6.7193
Max Act: 6.4693. Min Act: -0.1700
Data Index: 6572026 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7193. Min Range: -6.7193
Max Act: 6.4381. Min Act: -0.1700
Data Index: 4750944 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7193. Min Range: -6.7193
Max Act: 6.4381. Min Act: -0.1700
Data Index: 7779612 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7193. Min Range: -6.7193
Max Act: 6.4381. Min Act: -0.1700
Data Index: 1117771 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7193. Min Range: -6.7193
Max Act: 6.4381. Min Act: -0.1700
Data Index: 2933443 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #19