Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3156 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8974. Min Range: -7.8974
Max Act: 7.8974. Min Act: -0.1700
Data Index: 3793455 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8974. Min Range: -7.8974
Max Act: 7.6474. Min Act: -0.1700
Data Index: 5139480 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8974. Min Range: -7.8974
Max Act: 7.4911. Min Act: -0.1700
Data Index: 4570387 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8974. Min Range: -7.8974
Max Act: 7.3661. Min Act: -0.1700
Data Index: 6784199 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8974. Min Range: -7.8974
Max Act: 7.4286. Min Act: -0.1700
Data Index: 8248701 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8974. Min Range: -7.8974
Max Act: 7.3349. Min Act: -0.1700
Data Index: 5320439 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8974. Min Range: -7.8974
Max Act: 7.3661. Min Act: -0.1700
Data Index: 567743 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8974. Min Range: -7.8974
Max Act: 7.3349. Min Act: -0.1700
Data Index: 3270697 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8974. Min Range: -7.8974
Max Act: 7.3349. Min Act: -0.1700
Data Index: 6024132 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8974. Min Range: -7.8974
Max Act: 7.3036. Min Act: -0.1700
Data Index: 1107697 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8974. Min Range: -7.8974
Max Act: 7.2099. Min Act: -0.1700
Data Index: 2739602 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8974. Min Range: -7.8974
Max Act: 7.2099. Min Act: -0.1700
Data Index: 2262413 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8974. Min Range: -7.8974
Max Act: 7.1786. Min Act: -0.1700
Data Index: 4871651 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8974. Min Range: -7.8974
Max Act: 7.1474. Min Act: -0.1700
Data Index: 6317374 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8974. Min Range: -7.8974
Max Act: 7.1161. Min Act: -0.1700
Data Index: 465332 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8974. Min Range: -7.8974
Max Act: 7.0849. Min Act: -0.1700
Data Index: 559796 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8974. Min Range: -7.8974
Max Act: 7.0849. Min Act: -0.1700
Data Index: 2023533 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8974. Min Range: -7.8974
Max Act: 7.0536. Min Act: -0.1700
Data Index: 4714310 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8974. Min Range: -7.8974
Max Act: 7.0536. Min Act: -0.1700
Data Index: 6994105 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8974. Min Range: -7.8974
Max Act: 7.0536. Min Act: -0.1700
Data Index: 1741296 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #19