Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3817 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.5425. Min Range: -7.5425
Max Act: 7.5425. Min Act: -0.1700
Data Index: 3188620 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5425. Min Range: -7.5425
Max Act: 7.3862. Min Act: -0.1700
Data Index: 2363637 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5425. Min Range: -7.5425
Max Act: 7.3237. Min Act: -0.1700
Data Index: 564160 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5425. Min Range: -7.5425
Max Act: 7.2300. Min Act: -0.1700
Data Index: 5677488 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5425. Min Range: -7.5425
Max Act: 7.1987. Min Act: -0.1700
Data Index: 7353247 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5425. Min Range: -7.5425
Max Act: 7.1675. Min Act: -0.1700
Data Index: 5062723 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5425. Min Range: -7.5425
Max Act: 7.1675. Min Act: -0.1700
Data Index: 6039315 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5425. Min Range: -7.5425
Max Act: 7.1362. Min Act: -0.1700
Data Index: 731825 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5425. Min Range: -7.5425
Max Act: 7.1362. Min Act: -0.1700
Data Index: 4227949 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5425. Min Range: -7.5425
Max Act: 7.1362. Min Act: -0.1700
Data Index: 1835188 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5425. Min Range: -7.5425
Max Act: 7.0737. Min Act: -0.1700
Data Index: 186577 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5425. Min Range: -7.5425
Max Act: 7.0425. Min Act: -0.1700
Data Index: 3007644 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5425. Min Range: -7.5425
Max Act: 7.0737. Min Act: -0.1700
Data Index: 134565 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5425. Min Range: -7.5425
Max Act: 7.0112. Min Act: -0.1700
Data Index: 1894165 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5425. Min Range: -7.5425
Max Act: 7.1675. Min Act: -0.1700
Data Index: 4450318 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5425. Min Range: -7.5425
Max Act: 7.0112. Min Act: -0.1700
Data Index: 1261904 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5425. Min Range: -7.5425
Max Act: 7.0112. Min Act: -0.1700
Data Index: 7339832 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5425. Min Range: -7.5425
Max Act: 7.0425. Min Act: -0.1700
Data Index: 25191 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5425. Min Range: -7.5425
Max Act: 6.9175. Min Act: -0.1700
Data Index: 3490415 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5425. Min Range: -7.5425
Max Act: 6.9487. Min Act: -0.1700
Data Index: 3773846 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #19