Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 834 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3496. Min Range: -5.3496
Max Act: 5.3496. Min Act: -0.1700
Data Index: 927168 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3496. Min Range: -5.3496
Max Act: 5.3184. Min Act: -0.1700
Data Index: 321056 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3496. Min Range: -5.3496
Max Act: 5.3184. Min Act: -0.1700
Data Index: 8225910 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3496. Min Range: -5.3496
Max Act: 5.2559. Min Act: -0.1700
Data Index: 5494660 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3496. Min Range: -5.3496
Max Act: 5.2246. Min Act: -0.1700
Data Index: 3070551 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3496. Min Range: -5.3496
Max Act: 5.2246. Min Act: -0.1700
Data Index: 1391996 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3496. Min Range: -5.3496
Max Act: 5.1621. Min Act: -0.1700
Data Index: 98240 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3496. Min Range: -5.3496
Max Act: 5.2246. Min Act: -0.1700
Data Index: 1837350 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3496. Min Range: -5.3496
Max Act: 5.1934. Min Act: -0.1700
Data Index: 3907964 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3496. Min Range: -5.3496
Max Act: 5.1934. Min Act: -0.1700
Data Index: 2176958 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3496. Min Range: -5.3496
Max Act: 5.1621. Min Act: -0.1700
Data Index: 3370252 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3496. Min Range: -5.3496
Max Act: 5.1309. Min Act: -0.1700
Data Index: 8443190 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3496. Min Range: -5.3496
Max Act: 5.1309. Min Act: -0.1700
Data Index: 8382577 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3496. Min Range: -5.3496
Max Act: 5.1621. Min Act: -0.1700
Data Index: 1190300 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3496. Min Range: -5.3496
Max Act: 5.1309. Min Act: -0.1700
Data Index: 1554924 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3496. Min Range: -5.3496
Max Act: 5.0996. Min Act: -0.1700
Data Index: 2495084 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3496. Min Range: -5.3496
Max Act: 5.1309. Min Act: -0.1700
Data Index: 6226425 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3496. Min Range: -5.3496
Max Act: 5.1621. Min Act: -0.1700
Data Index: 5859919 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3496. Min Range: -5.3496
Max Act: 5.0996. Min Act: -0.1700
Data Index: 5395220 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3496. Min Range: -5.3496
Max Act: 5.1309. Min Act: -0.1700
Data Index: 1330035 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #19