Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2550 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6131. Min Range: -3.6131
Max Act: 3.6131. Min Act: -0.1700
Data Index: 1911637 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6131. Min Range: -3.6131
Max Act: 3.5818. Min Act: -0.1700
Data Index: 4151249 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6131. Min Range: -3.6131
Max Act: 3.5974. Min Act: -0.1700
Data Index: 6332608 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6131. Min Range: -3.6131
Max Act: 3.5818. Min Act: -0.1700
Data Index: 7654009 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6131. Min Range: -3.6131
Max Act: 3.4722. Min Act: -0.1700
Data Index: 33765 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6131. Min Range: -3.6131
Max Act: 3.4878. Min Act: -0.1700
Data Index: 652563 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6131. Min Range: -3.6131
Max Act: 3.4722. Min Act: -0.1700
Data Index: 3201021 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6131. Min Range: -3.6131
Max Act: 3.4722. Min Act: -0.1700
Data Index: 2828108 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6131. Min Range: -3.6131
Max Act: 3.4565. Min Act: -0.1700
Data Index: 7916802 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6131. Min Range: -3.6131
Max Act: 3.4408. Min Act: -0.1700
Data Index: 2761266 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6131. Min Range: -3.6131
Max Act: 3.4408. Min Act: -0.1700
Data Index: 3745706 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6131. Min Range: -3.6131
Max Act: 3.4252. Min Act: -0.1700
Data Index: 41626 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6131. Min Range: -3.6131
Max Act: 3.4095. Min Act: -0.1700
Data Index: 443413 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6131. Min Range: -3.6131
Max Act: 3.4095. Min Act: -0.1700
Data Index: 6114075 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6131. Min Range: -3.6131
Max Act: 3.4095. Min Act: -0.1700
Data Index: 3279903 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6131. Min Range: -3.6131
Max Act: 3.4252. Min Act: -0.1700
Data Index: 7188862 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6131. Min Range: -3.6131
Max Act: 3.4095. Min Act: -0.1700
Data Index: 5505119 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6131. Min Range: -3.6131
Max Act: 3.3938. Min Act: -0.1700
Data Index: 3590982 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6131. Min Range: -3.6131
Max Act: 3.4095. Min Act: -0.1700
Data Index: 5698597 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6131. Min Range: -3.6131
Max Act: 3.4252. Min Act: -0.1700
Data Index: 204840 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #19