Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3775 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2443. Min Range: -5.2443
Max Act: 5.2443. Min Act: -0.1700
Data Index: 8395846 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2443. Min Range: -5.2443
Max Act: 5.2443. Min Act: -0.1700
Data Index: 8462383 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2443. Min Range: -5.2443
Max Act: 5.1818. Min Act: -0.1700
Data Index: 2078074 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2443. Min Range: -5.2443
Max Act: 5.1818. Min Act: -0.1700
Data Index: 150994 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2443. Min Range: -5.2443
Max Act: 5.1193. Min Act: -0.1700
Data Index: 5839092 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2443. Min Range: -5.2443
Max Act: 5.0881. Min Act: -0.1700
Data Index: 7967164 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2443. Min Range: -5.2443
Max Act: 5.0568. Min Act: -0.1700
Data Index: 2557577 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2443. Min Range: -5.2443
Max Act: 5.0568. Min Act: -0.1700
Data Index: 2705377 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2443. Min Range: -5.2443
Max Act: 5.0568. Min Act: -0.1700
Data Index: 7875162 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2443. Min Range: -5.2443
Max Act: 5.0256. Min Act: -0.1700
Data Index: 5878815 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2443. Min Range: -5.2443
Max Act: 5.0256. Min Act: -0.1700
Data Index: 8447618 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2443. Min Range: -5.2443
Max Act: 5.0256. Min Act: -0.1700
Data Index: 8321365 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2443. Min Range: -5.2443
Max Act: 5.0568. Min Act: -0.1700
Data Index: 8692016 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2443. Min Range: -5.2443
Max Act: 5.0256. Min Act: -0.1700
Data Index: 7289640 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2443. Min Range: -5.2443
Max Act: 4.9943. Min Act: -0.1700
Data Index: 33176 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2443. Min Range: -5.2443
Max Act: 4.9943. Min Act: -0.1700
Data Index: 7464481 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2443. Min Range: -5.2443
Max Act: 4.9943. Min Act: -0.1700
Data Index: 5561290 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2443. Min Range: -5.2443
Max Act: 4.9943. Min Act: -0.1700
Data Index: 2127979 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2443. Min Range: -5.2443
Max Act: 5.0256. Min Act: -0.1700
Data Index: 600310 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2443. Min Range: -5.2443
Max Act: 4.9943. Min Act: -0.1700
Data Index: 6816847 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #19