Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2403 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8152. Min Range: -2.8152
Max Act: 2.8152. Min Act: -0.1700
Data Index: 4713454 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8152. Min Range: -2.8152
Max Act: 2.7993. Min Act: -0.1700
Data Index: 1844586 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8152. Min Range: -2.8152
Max Act: 2.5104. Min Act: -0.1700
Data Index: 7485510 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8152. Min Range: -2.8152
Max Act: 2.2653. Min Act: -0.1700
Data Index: 1987956 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8152. Min Range: -2.8152
Max Act: 2.2653. Min Act: -0.1700
Data Index: 545483 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8152. Min Range: -2.8152
Max Act: 2.2653. Min Act: -0.1700
Data Index: 7542648 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8152. Min Range: -2.8152
Max Act: 2.2488. Min Act: -0.1700
Data Index: 3254525 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8152. Min Range: -2.8152
Max Act: 2.2653. Min Act: -0.1700
Data Index: 7202394 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8152. Min Range: -2.8152
Max Act: 2.2818. Min Act: -0.1700
Data Index: 3984158 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8152. Min Range: -2.8152
Max Act: 2.2488. Min Act: -0.1700
Data Index: 6053501 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8152. Min Range: -2.8152
Max Act: 2.2157. Min Act: -0.1700
Data Index: 2479046 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8152. Min Range: -2.8152
Max Act: 2.1992. Min Act: -0.1700
Data Index: 980131 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8152. Min Range: -2.8152
Max Act: 2.1992. Min Act: -0.1700
Data Index: 1133167 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8152. Min Range: -2.8152
Max Act: 2.1992. Min Act: -0.1700
Data Index: 8177976 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8152. Min Range: -2.8152
Max Act: 2.1992. Min Act: -0.1700
Data Index: 4727615 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8152. Min Range: -2.8152
Max Act: 2.1659. Min Act: -0.1699
Data Index: 7204017 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8152. Min Range: -2.8152
Max Act: 2.1493. Min Act: -0.1699
Data Index: 1408545 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8152. Min Range: -2.8152
Max Act: 2.1825. Min Act: -0.1700
Data Index: 1340122 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8152. Min Range: -2.8152
Max Act: 2.1159. Min Act: -0.1700
Data Index: 588645 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8152. Min Range: -2.8152
Max Act: 2.1493. Min Act: -0.1700
Data Index: 5981596 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #19