Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2586 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8446. Min Range: -3.8446
Max Act: 3.8446. Min Act: -0.1700
Data Index: 4797512 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8446. Min Range: -3.8446
Max Act: 3.8446. Min Act: -0.1700
Data Index: 418159 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8446. Min Range: -3.8446
Max Act: 3.4847. Min Act: -0.1700
Data Index: 8034799 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8446. Min Range: -3.8446
Max Act: 3.3593. Min Act: -0.1700
Data Index: 7129300 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8446. Min Range: -3.8446
Max Act: 3.3279. Min Act: -0.1700
Data Index: 7662021 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8446. Min Range: -3.8446
Max Act: 3.3123. Min Act: -0.1700
Data Index: 3852862 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8446. Min Range: -3.8446
Max Act: 3.3279. Min Act: -0.1700
Data Index: 5688867 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8446. Min Range: -3.8446
Max Act: 3.3123. Min Act: -0.1700
Data Index: 7852130 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8446. Min Range: -3.8446
Max Act: 3.3123. Min Act: -0.1700
Data Index: 5069757 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8446. Min Range: -3.8446
Max Act: 3.2651. Min Act: -0.1700
Data Index: 2626070 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8446. Min Range: -3.8446
Max Act: 3.2651. Min Act: -0.1700
Data Index: 4765123 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8446. Min Range: -3.8446
Max Act: 3.2809. Min Act: -0.1700
Data Index: 2597710 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8446. Min Range: -3.8446
Max Act: 3.2651. Min Act: -0.1700
Data Index: 7463833 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8446. Min Range: -3.8446
Max Act: 3.2651. Min Act: -0.1700
Data Index: 4549103 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8446. Min Range: -3.8446
Max Act: 3.2337. Min Act: -0.1700
Data Index: 863745 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8446. Min Range: -3.8446
Max Act: 3.2180. Min Act: -0.1700
Data Index: 3417560 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8446. Min Range: -3.8446
Max Act: 3.2337. Min Act: -0.1700
Data Index: 4283363 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8446. Min Range: -3.8446
Max Act: 3.2337. Min Act: -0.1700
Data Index: 6900041 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8446. Min Range: -3.8446
Max Act: 3.2337. Min Act: -0.1700
Data Index: 7424378 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8446. Min Range: -3.8446
Max Act: 3.2023. Min Act: -0.1700
Data Index: 5062723 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #19