Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3038 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7217. Min Range: -7.7217
Max Act: 7.7217. Min Act: -0.1700
Data Index: 2119960 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7217. Min Range: -7.7217
Max Act: 7.1592. Min Act: -0.1700
Data Index: 4905651 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7217. Min Range: -7.7217
Max Act: 7.0967. Min Act: -0.1700
Data Index: 6384271 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7217. Min Range: -7.7217
Max Act: 7.0342. Min Act: -0.1700
Data Index: 7238781 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7217. Min Range: -7.7217
Max Act: 7.0029. Min Act: -0.1700
Data Index: 3610237 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7217. Min Range: -7.7217
Max Act: 6.9717. Min Act: -0.1700
Data Index: 8738554 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7217. Min Range: -7.7217
Max Act: 6.9717. Min Act: -0.1700
Data Index: 222978 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7217. Min Range: -7.7217
Max Act: 6.9404. Min Act: -0.1700
Data Index: 4094285 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7217. Min Range: -7.7217
Max Act: 6.8467. Min Act: -0.1700
Data Index: 6641642 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7217. Min Range: -7.7217
Max Act: 6.8154. Min Act: -0.1700
Data Index: 3424030 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7217. Min Range: -7.7217
Max Act: 6.8154. Min Act: -0.1700
Data Index: 904678 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7217. Min Range: -7.7217
Max Act: 6.7842. Min Act: -0.1700
Data Index: 8232347 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7217. Min Range: -7.7217
Max Act: 6.7217. Min Act: -0.1700
Data Index: 1316546 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7217. Min Range: -7.7217
Max Act: 6.7217. Min Act: -0.1700
Data Index: 1186448 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7217. Min Range: -7.7217
Max Act: 6.6904. Min Act: -0.1700
Data Index: 6374945 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7217. Min Range: -7.7217
Max Act: 6.6904. Min Act: -0.1700
Data Index: 584811 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7217. Min Range: -7.7217
Max Act: 6.6904. Min Act: -0.1700
Data Index: 6425347 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7217. Min Range: -7.7217
Max Act: 6.6904. Min Act: -0.1700
Data Index: 1632935 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7217. Min Range: -7.7217
Max Act: 6.6279. Min Act: -0.1700
Data Index: 2817301 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7217. Min Range: -7.7217
Max Act: 6.6592. Min Act: -0.1700
Data Index: 7560069 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #19