Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1462 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8291. Min Range: -7.8291
Max Act: 7.8291. Min Act: -0.1700
Data Index: 2781512 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8291. Min Range: -7.8291
Max Act: 7.7979. Min Act: -0.1700
Data Index: 3125678 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8291. Min Range: -7.8291
Max Act: 7.7979. Min Act: -0.1700
Data Index: 6788495 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8291. Min Range: -7.8291
Max Act: 7.7979. Min Act: -0.1700
Data Index: 5851159 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8291. Min Range: -7.8291
Max Act: 7.7666. Min Act: -0.1700
Data Index: 8672652 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8291. Min Range: -7.8291
Max Act: 7.6729. Min Act: -0.1700
Data Index: 4702165 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8291. Min Range: -7.8291
Max Act: 7.6416. Min Act: -0.1700
Data Index: 6419758 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8291. Min Range: -7.8291
Max Act: 7.6104. Min Act: -0.1700
Data Index: 3918300 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8291. Min Range: -7.8291
Max Act: 7.6416. Min Act: -0.1700
Data Index: 6396366 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8291. Min Range: -7.8291
Max Act: 7.6104. Min Act: -0.1700
Data Index: 6781019 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8291. Min Range: -7.8291
Max Act: 7.5791. Min Act: -0.1700
Data Index: 3170825 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8291. Min Range: -7.8291
Max Act: 7.5791. Min Act: -0.1700
Data Index: 1341530 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8291. Min Range: -7.8291
Max Act: 7.5479. Min Act: -0.1700
Data Index: 4483100 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8291. Min Range: -7.8291
Max Act: 7.5479. Min Act: -0.1700
Data Index: 2098948 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8291. Min Range: -7.8291
Max Act: 7.5479. Min Act: -0.1700
Data Index: 7381085 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8291. Min Range: -7.8291
Max Act: 7.5479. Min Act: -0.1700
Data Index: 7779776 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8291. Min Range: -7.8291
Max Act: 7.5166. Min Act: -0.1700
Data Index: 7591788 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8291. Min Range: -7.8291
Max Act: 7.5166. Min Act: -0.1700
Data Index: 4878023 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8291. Min Range: -7.8291
Max Act: 7.4854. Min Act: -0.1700
Data Index: 5083184 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8291. Min Range: -7.8291
Max Act: 7.4854. Min Act: -0.1700
Data Index: 1922556 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #19