Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1391 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4443. Min Range: -4.4443
Max Act: 4.4443. Min Act: -0.1700
Data Index: 7009360 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4443. Min Range: -4.4443
Max Act: 4.3818. Min Act: -0.1700
Data Index: 341306 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4443. Min Range: -4.4443
Max Act: 4.2881. Min Act: -0.1700
Data Index: 8756923 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4443. Min Range: -4.4443
Max Act: 4.2881. Min Act: -0.1700
Data Index: 7187169 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4443. Min Range: -4.4443
Max Act: 4.2256. Min Act: -0.1700
Data Index: 2013891 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4443. Min Range: -4.4443
Max Act: 4.2256. Min Act: -0.1700
Data Index: 4787581 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4443. Min Range: -4.4443
Max Act: 4.1943. Min Act: -0.1700
Data Index: 652357 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4443. Min Range: -4.4443
Max Act: 4.1631. Min Act: -0.1700
Data Index: 7181413 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4443. Min Range: -4.4443
Max Act: 4.1943. Min Act: -0.1700
Data Index: 7404898 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4443. Min Range: -4.4443
Max Act: 4.1943. Min Act: -0.1700
Data Index: 101616 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4443. Min Range: -4.4443
Max Act: 4.1943. Min Act: -0.1700
Data Index: 2958342 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4443. Min Range: -4.4443
Max Act: 4.1318. Min Act: -0.1700
Data Index: 7825511 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4443. Min Range: -4.4443
Max Act: 4.1631. Min Act: -0.1700
Data Index: 3389685 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4443. Min Range: -4.4443
Max Act: 4.1005. Min Act: -0.1700
Data Index: 6913793 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4443. Min Range: -4.4443
Max Act: 4.0693. Min Act: -0.1700
Data Index: 5303104 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4443. Min Range: -4.4443
Max Act: 4.0693. Min Act: -0.1700
Data Index: 5483065 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4443. Min Range: -4.4443
Max Act: 4.0693. Min Act: -0.1700
Data Index: 7768547 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4443. Min Range: -4.4443
Max Act: 4.0693. Min Act: -0.1700
Data Index: 4040585 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4443. Min Range: -4.4443
Max Act: 4.0693. Min Act: -0.1700
Data Index: 2629911 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4443. Min Range: -4.4443
Max Act: 4.0380. Min Act: -0.1700
Data Index: 6814644 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #19