Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3501 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5297. Min Range: -4.5297
Max Act: 4.5297. Min Act: -0.1700
Data Index: 5955429 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5297. Min Range: -4.5297
Max Act: 4.4985. Min Act: -0.1700
Data Index: 8736644 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5297. Min Range: -4.5297
Max Act: 4.3735. Min Act: -0.1700
Data Index: 3483016 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5297. Min Range: -4.5297
Max Act: 4.3422. Min Act: -0.1700
Data Index: 1443297 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5297. Min Range: -4.5297
Max Act: 4.2797. Min Act: -0.1700
Data Index: 3057268 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5297. Min Range: -4.5297
Max Act: 4.2485. Min Act: -0.1700
Data Index: 3521701 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5297. Min Range: -4.5297
Max Act: 4.2485. Min Act: -0.1700
Data Index: 830688 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5297. Min Range: -4.5297
Max Act: 4.2797. Min Act: -0.1700
Data Index: 7086313 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5297. Min Range: -4.5297
Max Act: 4.2797. Min Act: -0.1700
Data Index: 3650173 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5297. Min Range: -4.5297
Max Act: 4.2797. Min Act: -0.1700
Data Index: 251563 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5297. Min Range: -4.5297
Max Act: 4.2485. Min Act: -0.1700
Data Index: 1185642 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5297. Min Range: -4.5297
Max Act: 4.2485. Min Act: -0.1700
Data Index: 1336990 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5297. Min Range: -4.5297
Max Act: 4.2485. Min Act: -0.1700
Data Index: 3370869 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5297. Min Range: -4.5297
Max Act: 4.2172. Min Act: -0.1700
Data Index: 1475206 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5297. Min Range: -4.5297
Max Act: 4.2172. Min Act: -0.1700
Data Index: 3664706 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5297. Min Range: -4.5297
Max Act: 4.2172. Min Act: -0.1700
Data Index: 1221940 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5297. Min Range: -4.5297
Max Act: 4.2172. Min Act: -0.1700
Data Index: 1400192 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5297. Min Range: -4.5297
Max Act: 4.1860. Min Act: -0.1700
Data Index: 4438215 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5297. Min Range: -4.5297
Max Act: 4.2172. Min Act: -0.1700
Data Index: 4922655 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5297. Min Range: -4.5297
Max Act: 4.1860. Min Act: -0.1700
Data Index: 3167989 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19