Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5049 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7661. Min Range: -7.7661
Max Act: 7.7661. Min Act: -0.1700
Data Index: 6835997 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7661. Min Range: -7.7661
Max Act: 7.6098. Min Act: -0.1700
Data Index: 8204743 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7661. Min Range: -7.7661
Max Act: 7.6098. Min Act: -0.1700
Data Index: 2680718 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7661. Min Range: -7.7661
Max Act: 7.5473. Min Act: -0.1700
Data Index: 5572014 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7661. Min Range: -7.7661
Max Act: 7.5161. Min Act: -0.1700
Data Index: 5243790 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7661. Min Range: -7.7661
Max Act: 7.5161. Min Act: -0.1700
Data Index: 1857064 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7661. Min Range: -7.7661
Max Act: 7.4536. Min Act: -0.1700
Data Index: 3850595 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7661. Min Range: -7.7661
Max Act: 7.4223. Min Act: -0.1700
Data Index: 8671359 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7661. Min Range: -7.7661
Max Act: 7.4536. Min Act: -0.1700
Data Index: 3638595 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7661. Min Range: -7.7661
Max Act: 7.4536. Min Act: -0.1700
Data Index: 124833 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7661. Min Range: -7.7661
Max Act: 7.4223. Min Act: -0.1700
Data Index: 1368550 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7661. Min Range: -7.7661
Max Act: 7.4223. Min Act: -0.1700
Data Index: 1371428 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7661. Min Range: -7.7661
Max Act: 7.4223. Min Act: -0.1700
Data Index: 5428210 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7661. Min Range: -7.7661
Max Act: 7.3911. Min Act: -0.1700
Data Index: 1565808 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7661. Min Range: -7.7661
Max Act: 7.3911. Min Act: -0.1700
Data Index: 1771159 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7661. Min Range: -7.7661
Max Act: 7.3911. Min Act: -0.1700
Data Index: 2347619 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7661. Min Range: -7.7661
Max Act: 7.3286. Min Act: -0.1700
Data Index: 4675103 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7661. Min Range: -7.7661
Max Act: 7.3286. Min Act: -0.1700
Data Index: 1251843 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7661. Min Range: -7.7661
Max Act: 7.2973. Min Act: -0.1700
Data Index: 1418286 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7661. Min Range: -7.7661
Max Act: 7.2661. Min Act: -0.1700
Data Index: 1960101 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19