Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3496 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4960. Min Range: -5.4960
Max Act: 5.4960. Min Act: -0.1700
Data Index: 8043132 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4960. Min Range: -5.4960
Max Act: 5.4335. Min Act: -0.1700
Data Index: 5010814 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4960. Min Range: -5.4960
Max Act: 5.3397. Min Act: -0.1700
Data Index: 1610800 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4960. Min Range: -5.4960
Max Act: 5.3397. Min Act: -0.1700
Data Index: 4986895 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4960. Min Range: -5.4960
Max Act: 5.2772. Min Act: -0.1700
Data Index: 7630063 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4960. Min Range: -5.4960
Max Act: 5.2460. Min Act: -0.1700
Data Index: 7997820 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4960. Min Range: -5.4960
Max Act: 5.1835. Min Act: -0.1700
Data Index: 2759155 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4960. Min Range: -5.4960
Max Act: 5.1522. Min Act: -0.1700
Data Index: 6218898 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4960. Min Range: -5.4960
Max Act: 5.1835. Min Act: -0.1700
Data Index: 6751083 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4960. Min Range: -5.4960
Max Act: 5.1835. Min Act: -0.1700
Data Index: 6045397 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4960. Min Range: -5.4960
Max Act: 5.1522. Min Act: -0.1700
Data Index: 6486839 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4960. Min Range: -5.4960
Max Act: 5.1522. Min Act: -0.1700
Data Index: 4399040 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4960. Min Range: -5.4960
Max Act: 5.1210. Min Act: -0.1700
Data Index: 5029562 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4960. Min Range: -5.4960
Max Act: 5.1210. Min Act: -0.1700
Data Index: 6378248 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4960. Min Range: -5.4960
Max Act: 5.1210. Min Act: -0.1700
Data Index: 1486047 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4960. Min Range: -5.4960
Max Act: 5.0897. Min Act: -0.1700
Data Index: 252835 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4960. Min Range: -5.4960
Max Act: 5.1210. Min Act: -0.1700
Data Index: 8452679 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4960. Min Range: -5.4960
Max Act: 5.0897. Min Act: -0.1700
Data Index: 7361352 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4960. Min Range: -5.4960
Max Act: 5.1210. Min Act: -0.1700
Data Index: 8683933 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4960. Min Range: -5.4960
Max Act: 5.0585. Min Act: -0.1700
Data Index: 4160159 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #19