Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2588 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1965. Min Range: -3.1965
Max Act: 3.1965. Min Act: -0.1700
Data Index: 2098138 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1965. Min Range: -3.1965
Max Act: 3.1965. Min Act: -0.1700
Data Index: 4845123 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1965. Min Range: -3.1965
Max Act: 3.1493. Min Act: -0.1700
Data Index: 5112964 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1965. Min Range: -3.1965
Max Act: 3.1493. Min Act: -0.1700
Data Index: 201048 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1965. Min Range: -3.1965
Max Act: 3.1493. Min Act: -0.1700
Data Index: 5021903 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1965. Min Range: -3.1965
Max Act: 3.1335. Min Act: -0.1700
Data Index: 4868854 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1965. Min Range: -3.1965
Max Act: 3.1020. Min Act: -0.1700
Data Index: 1088001 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1965. Min Range: -3.1965
Max Act: 3.1020. Min Act: -0.1700
Data Index: 6263843 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1965. Min Range: -3.1965
Max Act: 3.0705. Min Act: -0.1700
Data Index: 3302594 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1965. Min Range: -3.1965
Max Act: 3.1020. Min Act: -0.1700
Data Index: 6758768 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1965. Min Range: -3.1965
Max Act: 3.1020. Min Act: -0.1700
Data Index: 3667780 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1965. Min Range: -3.1965
Max Act: 3.1020. Min Act: -0.1700
Data Index: 8028560 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1965. Min Range: -3.1965
Max Act: 3.0705. Min Act: -0.1700
Data Index: 6900475 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1965. Min Range: -3.1965
Max Act: 3.0547. Min Act: -0.1700
Data Index: 317832 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1965. Min Range: -3.1965
Max Act: 3.0863. Min Act: -0.1700
Data Index: 3790681 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1965. Min Range: -3.1965
Max Act: 3.0705. Min Act: -0.1700
Data Index: 1195669 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1965. Min Range: -3.1965
Max Act: 3.0547. Min Act: -0.1700
Data Index: 623616 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1965. Min Range: -3.1965
Max Act: 3.0547. Min Act: -0.1700
Data Index: 1748766 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1965. Min Range: -3.1965
Max Act: 3.0547. Min Act: -0.1700
Data Index: 3426737 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1965. Min Range: -3.1965
Max Act: 3.0547. Min Act: -0.1700
Data Index: 4335547 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #19