Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2500 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4306. Min Range: -5.4306
Max Act: 5.4306. Min Act: -0.1700
Data Index: 7308343 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4306. Min Range: -5.4306
Max Act: 5.3056. Min Act: -0.1700
Data Index: 8123573 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4306. Min Range: -5.4306
Max Act: 5.2743. Min Act: -0.1700
Data Index: 2543136 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4306. Min Range: -5.4306
Max Act: 5.2431. Min Act: -0.1700
Data Index: 4698508 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4306. Min Range: -5.4306
Max Act: 5.2431. Min Act: -0.1700
Data Index: 63935 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4306. Min Range: -5.4306
Max Act: 5.2431. Min Act: -0.1700
Data Index: 3562781 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4306. Min Range: -5.4306
Max Act: 5.2431. Min Act: -0.1700
Data Index: 3102531 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4306. Min Range: -5.4306
Max Act: 5.1806. Min Act: -0.1700
Data Index: 7254369 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4306. Min Range: -5.4306
Max Act: 5.2118. Min Act: -0.1700
Data Index: 8528262 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4306. Min Range: -5.4306
Max Act: 5.1806. Min Act: -0.1700
Data Index: 1371602 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4306. Min Range: -5.4306
Max Act: 5.1493. Min Act: -0.1700
Data Index: 5269529 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4306. Min Range: -5.4306
Max Act: 5.1493. Min Act: -0.1700
Data Index: 4552866 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4306. Min Range: -5.4306
Max Act: 5.1806. Min Act: -0.1700
Data Index: 2840654 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4306. Min Range: -5.4306
Max Act: 5.1181. Min Act: -0.1700
Data Index: 7617066 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4306. Min Range: -5.4306
Max Act: 5.1806. Min Act: -0.1700
Data Index: 2081532 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4306. Min Range: -5.4306
Max Act: 5.1493. Min Act: -0.1700
Data Index: 830152 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4306. Min Range: -5.4306
Max Act: 5.0868. Min Act: -0.1700
Data Index: 5478441 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4306. Min Range: -5.4306
Max Act: 5.1181. Min Act: -0.1700
Data Index: 8018005 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4306. Min Range: -5.4306
Max Act: 5.1493. Min Act: -0.1700
Data Index: 7585262 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4306. Min Range: -5.4306
Max Act: 5.0868. Min Act: -0.1700
Data Index: 1257076 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #19