Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3623 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6445. Min Range: -9.6445
Max Act: 9.6445. Min Act: -0.1700
Data Index: 7160863 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6445. Min Range: -9.6445
Max Act: 9.6445. Min Act: -0.1700
Data Index: 1832841 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6445. Min Range: -9.6445
Max Act: 9.3320. Min Act: -0.1700
Data Index: 1553280 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6445. Min Range: -9.6445
Max Act: 9.1445. Min Act: -0.1700
Data Index: 6119830 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6445. Min Range: -9.6445
Max Act: 9.2070. Min Act: -0.1700
Data Index: 36676 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6445. Min Range: -9.6445
Max Act: 9.0195. Min Act: -0.1700
Data Index: 3747669 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6445. Min Range: -9.6445
Max Act: 9.0195. Min Act: -0.1700
Data Index: 3832065 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6445. Min Range: -9.6445
Max Act: 8.9570. Min Act: -0.1700
Data Index: 3381154 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6445. Min Range: -9.6445
Max Act: 8.9570. Min Act: -0.1700
Data Index: 5540204 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6445. Min Range: -9.6445
Max Act: 8.9570. Min Act: -0.1700
Data Index: 3182962 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6445. Min Range: -9.6445
Max Act: 8.8320. Min Act: -0.1700
Data Index: 923945 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6445. Min Range: -9.6445
Max Act: 8.8945. Min Act: -0.1700
Data Index: 3830781 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6445. Min Range: -9.6445
Max Act: 8.8945. Min Act: -0.1700
Data Index: 5265324 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6445. Min Range: -9.6445
Max Act: 8.8320. Min Act: -0.1700
Data Index: 5482374 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6445. Min Range: -9.6445
Max Act: 8.8320. Min Act: -0.1700
Data Index: 697193 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6445. Min Range: -9.6445
Max Act: 8.8320. Min Act: -0.1700
Data Index: 2666546 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6445. Min Range: -9.6445
Max Act: 8.8320. Min Act: -0.1700
Data Index: 7896286 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6445. Min Range: -9.6445
Max Act: 8.7695. Min Act: -0.1700
Data Index: 4152703 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6445. Min Range: -9.6445
Max Act: 8.7695. Min Act: -0.1700
Data Index: 6653208 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6445. Min Range: -9.6445
Max Act: 8.7070. Min Act: -0.1700
Data Index: 5309558 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #19