Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4086 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.3735. Min Range: -2.3735
Max Act: 2.3571. Min Act: -0.1700
Data Index: 6555292 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3735. Min Range: -2.3735
Max Act: 2.3735. Min Act: -0.1700
Data Index: 3158158 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3735. Min Range: -2.3735
Max Act: 2.3408. Min Act: -0.1700
Data Index: 8602995 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3735. Min Range: -2.3735
Max Act: 2.2915. Min Act: -0.1700
Data Index: 7574353 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3735. Min Range: -2.3735
Max Act: 2.3079. Min Act: -0.1700
Data Index: 6741178 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3735. Min Range: -2.3735
Max Act: 2.3079. Min Act: -0.1700
Data Index: 7103519 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3735. Min Range: -2.3735
Max Act: 2.3079. Min Act: -0.1700
Data Index: 7477863 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3735. Min Range: -2.3735
Max Act: 2.2915. Min Act: -0.1700
Data Index: 5020275 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3735. Min Range: -2.3735
Max Act: 2.2750. Min Act: -0.1700
Data Index: 7448524 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3735. Min Range: -2.3735
Max Act: 2.2915. Min Act: -0.1700
Data Index: 5599040 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3735. Min Range: -2.3735
Max Act: 2.2750. Min Act: -0.1700
Data Index: 2948474 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3735. Min Range: -2.3735
Max Act: 2.2750. Min Act: -0.1700
Data Index: 853912 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3735. Min Range: -2.3735
Max Act: 2.2915. Min Act: -0.1700
Data Index: 7473727 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3735. Min Range: -2.3735
Max Act: 2.2750. Min Act: -0.1700
Data Index: 6170442 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3735. Min Range: -2.3735
Max Act: 2.2750. Min Act: -0.1700
Data Index: 3909118 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3735. Min Range: -2.3735
Max Act: 2.2585. Min Act: -0.1700
Data Index: 1859877 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3735. Min Range: -2.3735
Max Act: 2.2420. Min Act: -0.1700
Data Index: 2757118 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3735. Min Range: -2.3735
Max Act: 2.2420. Min Act: -0.1700
Data Index: 6186531 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3735. Min Range: -2.3735
Max Act: 2.2585. Min Act: -0.1700
Data Index: 465143 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3735. Min Range: -2.3735
Max Act: 2.2254. Min Act: -0.1700
Data Index: 6486807 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #19