Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1583 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3143. Min Range: -5.3143
Max Act: 5.3143. Min Act: -0.1700
Data Index: 1770800 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3143. Min Range: -5.3143
Max Act: 5.1893. Min Act: -0.1700
Data Index: 299568 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3143. Min Range: -5.3143
Max Act: 5.0331. Min Act: -0.1700
Data Index: 115216 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3143. Min Range: -5.3143
Max Act: 5.0643. Min Act: -0.1700
Data Index: 5382655 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3143. Min Range: -5.3143
Max Act: 5.0643. Min Act: -0.1700
Data Index: 8393247 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3143. Min Range: -5.3143
Max Act: 5.0643. Min Act: -0.1700
Data Index: 2515357 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3143. Min Range: -5.3143
Max Act: 5.0331. Min Act: -0.1700
Data Index: 1244626 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3143. Min Range: -5.3143
Max Act: 5.0018. Min Act: -0.1700
Data Index: 3065771 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3143. Min Range: -5.3143
Max Act: 5.0018. Min Act: -0.1700
Data Index: 5672559 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3143. Min Range: -5.3143
Max Act: 5.0018. Min Act: -0.1700
Data Index: 5484397 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3143. Min Range: -5.3143
Max Act: 4.9706. Min Act: -0.1700
Data Index: 2876130 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3143. Min Range: -5.3143
Max Act: 4.9706. Min Act: -0.1700
Data Index: 95220 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3143. Min Range: -5.3143
Max Act: 4.9706. Min Act: -0.1700
Data Index: 6161219 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3143. Min Range: -5.3143
Max Act: 4.9706. Min Act: -0.1700
Data Index: 5988287 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3143. Min Range: -5.3143
Max Act: 4.9706. Min Act: -0.1700
Data Index: 6630144 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3143. Min Range: -5.3143
Max Act: 4.9706. Min Act: -0.1700
Data Index: 5904920 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3143. Min Range: -5.3143
Max Act: 4.9393. Min Act: -0.1700
Data Index: 270166 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3143. Min Range: -5.3143
Max Act: 4.9393. Min Act: -0.1700
Data Index: 6253379 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3143. Min Range: -5.3143
Max Act: 4.9393. Min Act: -0.1700
Data Index: 896457 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3143. Min Range: -5.3143
Max Act: 4.9393. Min Act: -0.1700
Data Index: 7565125 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #19