Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 741 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8557. Min Range: -1.8557
Max Act: 1.8557. Min Act: -0.1700
Data Index: 7693243 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8557. Min Range: -1.8557
Max Act: 1.8557. Min Act: -0.1700
Data Index: 7693249 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8557. Min Range: -1.8557
Max Act: 1.8386. Min Act: -0.1700
Data Index: 6604866 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8557. Min Range: -1.8557
Max Act: 1.8128. Min Act: -0.1699
Data Index: 7693246 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8557. Min Range: -1.8557
Max Act: 1.8042. Min Act: -0.1700
Data Index: 7632835 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8557. Min Range: -1.8557
Max Act: 1.7956. Min Act: -0.1700
Data Index: 2655845 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8557. Min Range: -1.8557
Max Act: 1.7698. Min Act: -0.1700
Data Index: 236250 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8557. Min Range: -1.8557
Max Act: 1.7698. Min Act: -0.1700
Data Index: 259024 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8557. Min Range: -1.8557
Max Act: 1.7611. Min Act: -0.1700
Data Index: 8593329 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8557. Min Range: -1.8557
Max Act: 1.7439. Min Act: -0.1700
Data Index: 1112864 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8557. Min Range: -1.8557
Max Act: 1.7611. Min Act: -0.1700
Data Index: 5507939 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8557. Min Range: -1.8557
Max Act: 1.7525. Min Act: -0.1700
Data Index: 1578851 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8557. Min Range: -1.8557
Max Act: 1.7611. Min Act: -0.1700
Data Index: 4012305 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8557. Min Range: -1.8557
Max Act: 1.7439. Min Act: -0.1700
Data Index: 2037090 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8557. Min Range: -1.8557
Max Act: 1.7611. Min Act: -0.1700
Data Index: 5208662 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8557. Min Range: -1.8557
Max Act: 1.7525. Min Act: -0.1700
Data Index: 6059712 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8557. Min Range: -1.8557
Max Act: 1.7352. Min Act: -0.1700
Data Index: 6183888 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8557. Min Range: -1.8557
Max Act: 1.7439. Min Act: -0.1700
Data Index: 4690808 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8557. Min Range: -1.8557
Max Act: 1.7439. Min Act: -0.1700
Data Index: 1530110 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8557. Min Range: -1.8557
Max Act: 1.7439. Min Act: -0.1700
Data Index: 7688216 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #19