Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1170 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7281. Min Range: -6.7281
Max Act: 6.7281. Min Act: -0.1700
Data Index: 2054388 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7281. Min Range: -6.7281
Max Act: 6.3843. Min Act: -0.1700
Data Index: 472143 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7281. Min Range: -6.7281
Max Act: 6.3218. Min Act: -0.1700
Data Index: 5862811 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7281. Min Range: -6.7281
Max Act: 6.3218. Min Act: -0.1700
Data Index: 1769012 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7281. Min Range: -6.7281
Max Act: 6.2906. Min Act: -0.1700
Data Index: 5412515 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7281. Min Range: -6.7281
Max Act: 6.2906. Min Act: -0.1700
Data Index: 2226461 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7281. Min Range: -6.7281
Max Act: 6.2593. Min Act: -0.1700
Data Index: 70594 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7281. Min Range: -6.7281
Max Act: 6.2593. Min Act: -0.1700
Data Index: 1987020 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7281. Min Range: -6.7281
Max Act: 6.2281. Min Act: -0.1700
Data Index: 1987019 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7281. Min Range: -6.7281
Max Act: 6.1968. Min Act: -0.1700
Data Index: 5388252 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7281. Min Range: -6.7281
Max Act: 6.1968. Min Act: -0.1700
Data Index: 1734282 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7281. Min Range: -6.7281
Max Act: 6.1968. Min Act: -0.1700
Data Index: 4477000 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7281. Min Range: -6.7281
Max Act: 6.1968. Min Act: -0.1700
Data Index: 2615236 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7281. Min Range: -6.7281
Max Act: 6.1656. Min Act: -0.1700
Data Index: 2047920 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7281. Min Range: -6.7281
Max Act: 6.1656. Min Act: -0.1700
Data Index: 947624 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7281. Min Range: -6.7281
Max Act: 6.1343. Min Act: -0.1700
Data Index: 4901723 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7281. Min Range: -6.7281
Max Act: 6.1031. Min Act: -0.1700
Data Index: 3774741 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7281. Min Range: -6.7281
Max Act: 6.1656. Min Act: -0.1700
Data Index: 2587071 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7281. Min Range: -6.7281
Max Act: 6.1343. Min Act: -0.1700
Data Index: 4782502 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7281. Min Range: -6.7281
Max Act: 6.1343. Min Act: -0.1700
Data Index: 1232603 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #19