Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2140 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.5248. Min Range: -7.5248
Max Act: 7.5248. Min Act: -0.1700
Data Index: 6086173 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5248. Min Range: -7.5248
Max Act: 7.5248. Min Act: -0.1700
Data Index: 109715 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5248. Min Range: -7.5248
Max Act: 7.4623. Min Act: -0.1700
Data Index: 4048780 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5248. Min Range: -7.5248
Max Act: 7.4623. Min Act: -0.1700
Data Index: 5258035 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5248. Min Range: -7.5248
Max Act: 7.3060. Min Act: -0.1700
Data Index: 2436635 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5248. Min Range: -7.5248
Max Act: 7.2748. Min Act: -0.1700
Data Index: 6456478 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5248. Min Range: -7.5248
Max Act: 7.2748. Min Act: -0.1700
Data Index: 7246091 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5248. Min Range: -7.5248
Max Act: 7.2435. Min Act: -0.1700
Data Index: 5953667 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5248. Min Range: -7.5248
Max Act: 7.2123. Min Act: -0.1700
Data Index: 7378323 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5248. Min Range: -7.5248
Max Act: 7.2123. Min Act: -0.1700
Data Index: 8675332 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5248. Min Range: -7.5248
Max Act: 7.1810. Min Act: -0.1700
Data Index: 1557451 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5248. Min Range: -7.5248
Max Act: 7.2123. Min Act: -0.1700
Data Index: 8264570 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5248. Min Range: -7.5248
Max Act: 7.1185. Min Act: -0.1700
Data Index: 7977073 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5248. Min Range: -7.5248
Max Act: 7.1498. Min Act: -0.1700
Data Index: 6733114 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5248. Min Range: -7.5248
Max Act: 7.0873. Min Act: -0.1700
Data Index: 3327508 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5248. Min Range: -7.5248
Max Act: 7.1185. Min Act: -0.1700
Data Index: 4916738 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5248. Min Range: -7.5248
Max Act: 7.1185. Min Act: -0.1700
Data Index: 7655207 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5248. Min Range: -7.5248
Max Act: 7.0560. Min Act: -0.1700
Data Index: 847877 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5248. Min Range: -7.5248
Max Act: 7.1185. Min Act: -0.1700
Data Index: 8052256 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5248. Min Range: -7.5248
Max Act: 7.1185. Min Act: -0.1700
Data Index: 516408 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #19