Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2573 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5165. Min Range: -5.5165
Max Act: 5.5165. Min Act: -0.1700
Data Index: 8671156 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5165. Min Range: -5.5165
Max Act: 5.4852. Min Act: -0.1700
Data Index: 6223418 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5165. Min Range: -5.5165
Max Act: 5.4852. Min Act: -0.1700
Data Index: 1327363 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5165. Min Range: -5.5165
Max Act: 5.4540. Min Act: -0.1700
Data Index: 2759979 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5165. Min Range: -5.5165
Max Act: 5.4540. Min Act: -0.1700
Data Index: 8599590 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5165. Min Range: -5.5165
Max Act: 5.4227. Min Act: -0.1700
Data Index: 954918 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5165. Min Range: -5.5165
Max Act: 5.3602. Min Act: -0.1700
Data Index: 6547987 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5165. Min Range: -5.5165
Max Act: 5.3602. Min Act: -0.1700
Data Index: 6866964 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5165. Min Range: -5.5165
Max Act: 5.2977. Min Act: -0.1700
Data Index: 5682552 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5165. Min Range: -5.5165
Max Act: 5.3290. Min Act: -0.1700
Data Index: 1048649 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5165. Min Range: -5.5165
Max Act: 5.2977. Min Act: -0.1700
Data Index: 4347226 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5165. Min Range: -5.5165
Max Act: 5.3290. Min Act: -0.1700
Data Index: 942781 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5165. Min Range: -5.5165
Max Act: 5.2977. Min Act: -0.1700
Data Index: 4120160 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5165. Min Range: -5.5165
Max Act: 5.2665. Min Act: -0.1700
Data Index: 4735689 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5165. Min Range: -5.5165
Max Act: 5.2352. Min Act: -0.1700
Data Index: 2687169 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5165. Min Range: -5.5165
Max Act: 5.2665. Min Act: -0.1700
Data Index: 2633636 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5165. Min Range: -5.5165
Max Act: 5.2977. Min Act: -0.1700
Data Index: 3289462 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5165. Min Range: -5.5165
Max Act: 5.2665. Min Act: -0.1700
Data Index: 2521221 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5165. Min Range: -5.5165
Max Act: 5.2665. Min Act: -0.1700
Data Index: 3992546 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5165. Min Range: -5.5165
Max Act: 5.2665. Min Act: -0.1700
Data Index: 632231 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #19