Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3066 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9190. Min Range: -5.9190
Max Act: 5.9190. Min Act: -0.1700
Data Index: 3072468 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9190. Min Range: -5.9190
Max Act: 5.8565. Min Act: -0.1700
Data Index: 8427373 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9190. Min Range: -5.9190
Max Act: 5.7628. Min Act: -0.1700
Data Index: 6831000 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9190. Min Range: -5.9190
Max Act: 5.7628. Min Act: -0.1700
Data Index: 6769852 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9190. Min Range: -5.9190
Max Act: 5.7315. Min Act: -0.1700
Data Index: 3096131 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9190. Min Range: -5.9190
Max Act: 5.7315. Min Act: -0.1700
Data Index: 7065026 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9190. Min Range: -5.9190
Max Act: 5.6690. Min Act: -0.1700
Data Index: 3664048 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9190. Min Range: -5.9190
Max Act: 5.6690. Min Act: -0.1700
Data Index: 8658345 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9190. Min Range: -5.9190
Max Act: 5.6690. Min Act: -0.1700
Data Index: 4498198 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9190. Min Range: -5.9190
Max Act: 5.6690. Min Act: -0.1700
Data Index: 7065028 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9190. Min Range: -5.9190
Max Act: 5.6378. Min Act: -0.1700
Data Index: 6596857 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9190. Min Range: -5.9190
Max Act: 5.6378. Min Act: -0.1700
Data Index: 2866987 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9190. Min Range: -5.9190
Max Act: 5.6378. Min Act: -0.1700
Data Index: 2203337 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9190. Min Range: -5.9190
Max Act: 5.6065. Min Act: -0.1700
Data Index: 2548068 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9190. Min Range: -5.9190
Max Act: 5.6065. Min Act: -0.1700
Data Index: 3938761 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9190. Min Range: -5.9190
Max Act: 5.5753. Min Act: -0.1700
Data Index: 3072470 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9190. Min Range: -5.9190
Max Act: 5.5753. Min Act: -0.1700
Data Index: 3124858 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9190. Min Range: -5.9190
Max Act: 5.5753. Min Act: -0.1700
Data Index: 7601507 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9190. Min Range: -5.9190
Max Act: 5.5753. Min Act: -0.1700
Data Index: 5049713 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9190. Min Range: -5.9190
Max Act: 5.5753. Min Act: -0.1700
Data Index: 3096135 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #19