Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 47 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.6870. Min Range: -1.6870
Max Act: 1.6870. Min Act: -0.1700
Data Index: 5664928 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6870. Min Range: -1.6870
Max Act: 1.6435. Min Act: -0.1700
Data Index: 7603753 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6870. Min Range: -1.6870
Max Act: 1.6348. Min Act: -0.1700
Data Index: 882897 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6870. Min Range: -1.6870
Max Act: 1.6261. Min Act: -0.1700
Data Index: 812144 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6870. Min Range: -1.6870
Max Act: 1.6173. Min Act: -0.1700
Data Index: 1188035 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6870. Min Range: -1.6870
Max Act: 1.6173. Min Act: -0.1700
Data Index: 7520790 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6870. Min Range: -1.6870
Max Act: 1.6086. Min Act: -0.1700
Data Index: 2196226 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6870. Min Range: -1.6870
Max Act: 1.6173. Min Act: -0.1700
Data Index: 5143420 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6870. Min Range: -1.6870
Max Act: 1.6086. Min Act: -0.1700
Data Index: 7804301 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6870. Min Range: -1.6870
Max Act: 1.5999. Min Act: -0.1700
Data Index: 5031767 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6870. Min Range: -1.6870
Max Act: 1.5999. Min Act: -0.1700
Data Index: 7894250 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6870. Min Range: -1.6870
Max Act: 1.5912. Min Act: -0.1700
Data Index: 2008042 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6870. Min Range: -1.6870
Max Act: 1.5824. Min Act: -0.1700
Data Index: 2706318 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6870. Min Range: -1.6870
Max Act: 1.5824. Min Act: -0.1700
Data Index: 1334442 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6870. Min Range: -1.6870
Max Act: 1.5737. Min Act: -0.1700
Data Index: 3679017 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6870. Min Range: -1.6870
Max Act: 1.5824. Min Act: -0.1700
Data Index: 2236956 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6870. Min Range: -1.6870
Max Act: 1.5824. Min Act: -0.1700
Data Index: 2347863 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6870. Min Range: -1.6870
Max Act: 1.5737. Min Act: -0.1700
Data Index: 8355906 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6870. Min Range: -1.6870
Max Act: 1.5562. Min Act: -0.1700
Data Index: 4347421 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6870. Min Range: -1.6870
Max Act: 1.5562. Min Act: -0.1700
Data Index: 2388842 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #19