Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3332 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3257. Min Range: -6.3257
Max Act: 6.3257. Min Act: -0.1700
Data Index: 8297039 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3257. Min Range: -6.3257
Max Act: 6.1695. Min Act: -0.1700
Data Index: 5983499 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3257. Min Range: -6.3257
Max Act: 6.0132. Min Act: -0.1700
Data Index: 8297040 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3257. Min Range: -6.3257
Max Act: 5.9195. Min Act: -0.1700
Data Index: 44801 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3257. Min Range: -6.3257
Max Act: 5.7632. Min Act: -0.1700
Data Index: 2295231 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3257. Min Range: -6.3257
Max Act: 5.7320. Min Act: -0.1700
Data Index: 2007330 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3257. Min Range: -6.3257
Max Act: 5.7320. Min Act: -0.1700
Data Index: 8173050 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3257. Min Range: -6.3257
Max Act: 5.6695. Min Act: -0.1700
Data Index: 841375 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3257. Min Range: -6.3257
Max Act: 5.6070. Min Act: -0.1700
Data Index: 5392889 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3257. Min Range: -6.3257
Max Act: 5.5757. Min Act: -0.1700
Data Index: 44800 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3257. Min Range: -6.3257
Max Act: 5.5757. Min Act: -0.1700
Data Index: 5668883 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3257. Min Range: -6.3257
Max Act: 5.5757. Min Act: -0.1700
Data Index: 869778 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3257. Min Range: -6.3257
Max Act: 5.5445. Min Act: -0.1700
Data Index: 8305686 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3257. Min Range: -6.3257
Max Act: 5.5445. Min Act: -0.1700
Data Index: 6441545 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3257. Min Range: -6.3257
Max Act: 5.5445. Min Act: -0.1700
Data Index: 6326992 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3257. Min Range: -6.3257
Max Act: 5.4820. Min Act: -0.1700
Data Index: 5532448 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3257. Min Range: -6.3257
Max Act: 5.5445. Min Act: -0.1700
Data Index: 6026988 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3257. Min Range: -6.3257
Max Act: 5.4820. Min Act: -0.1700
Data Index: 1039839 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3257. Min Range: -6.3257
Max Act: 5.5132. Min Act: -0.1700
Data Index: 4359520 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3257. Min Range: -6.3257
Max Act: 5.4820. Min Act: -0.1700
Data Index: 7351805 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #19