Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4080 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7168. Min Range: -5.7168
Max Act: 5.7168. Min Act: -0.1700
Data Index: 7830021 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7168. Min Range: -5.7168
Max Act: 5.6543. Min Act: -0.1700
Data Index: 5423529 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7168. Min Range: -5.7168
Max Act: 5.5605. Min Act: -0.1700
Data Index: 7448202 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7168. Min Range: -5.7168
Max Act: 5.5293. Min Act: -0.1700
Data Index: 8325417 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7168. Min Range: -5.7168
Max Act: 5.5293. Min Act: -0.1700
Data Index: 2024502 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7168. Min Range: -5.7168
Max Act: 5.5293. Min Act: -0.1700
Data Index: 4669560 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7168. Min Range: -5.7168
Max Act: 5.5293. Min Act: -0.1700
Data Index: 2224274 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7168. Min Range: -5.7168
Max Act: 5.4668. Min Act: -0.1700
Data Index: 7911649 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7168. Min Range: -5.7168
Max Act: 5.4355. Min Act: -0.1700
Data Index: 223383 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7168. Min Range: -5.7168
Max Act: 5.4355. Min Act: -0.1700
Data Index: 3594094 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7168. Min Range: -5.7168
Max Act: 5.4355. Min Act: -0.1700
Data Index: 6949403 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7168. Min Range: -5.7168
Max Act: 5.4355. Min Act: -0.1700
Data Index: 2333113 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7168. Min Range: -5.7168
Max Act: 5.4043. Min Act: -0.1700
Data Index: 7344246 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7168. Min Range: -5.7168
Max Act: 5.4043. Min Act: -0.1700
Data Index: 984364 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7168. Min Range: -5.7168
Max Act: 5.4043. Min Act: -0.1700
Data Index: 47064 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7168. Min Range: -5.7168
Max Act: 5.3730. Min Act: -0.1700
Data Index: 4473269 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7168. Min Range: -5.7168
Max Act: 5.3418. Min Act: -0.1700
Data Index: 3105621 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7168. Min Range: -5.7168
Max Act: 5.3730. Min Act: -0.1700
Data Index: 6557076 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7168. Min Range: -5.7168
Max Act: 5.3730. Min Act: -0.1700
Data Index: 5646566 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7168. Min Range: -5.7168
Max Act: 5.3418. Min Act: -0.1700
Data Index: 30709 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #19