Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 72 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7098. Min Range: -4.7098
Max Act: 4.7098. Min Act: -0.1700
Data Index: 1235166 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7098. Min Range: -4.7098
Max Act: 4.4911. Min Act: -0.1700
Data Index: 4787634 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7098. Min Range: -4.7098
Max Act: 4.3660. Min Act: -0.1700
Data Index: 4179163 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7098. Min Range: -4.7098
Max Act: 4.3035. Min Act: -0.1700
Data Index: 5316386 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7098. Min Range: -4.7098
Max Act: 4.2410. Min Act: -0.1700
Data Index: 4177747 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7098. Min Range: -4.7098
Max Act: 4.2410. Min Act: -0.1700
Data Index: 5934111 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7098. Min Range: -4.7098
Max Act: 4.2410. Min Act: -0.1700
Data Index: 5237539 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7098. Min Range: -4.7098
Max Act: 4.2098. Min Act: -0.1700
Data Index: 6922532 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7098. Min Range: -4.7098
Max Act: 4.2098. Min Act: -0.1700
Data Index: 7083902 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7098. Min Range: -4.7098
Max Act: 4.2098. Min Act: -0.1700
Data Index: 8558411 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7098. Min Range: -4.7098
Max Act: 4.2098. Min Act: -0.1700
Data Index: 5474899 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7098. Min Range: -4.7098
Max Act: 4.2410. Min Act: -0.1700
Data Index: 6747664 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7098. Min Range: -4.7098
Max Act: 4.1473. Min Act: -0.1700
Data Index: 7338466 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7098. Min Range: -4.7098
Max Act: 4.1785. Min Act: -0.1700
Data Index: 7592897 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7098. Min Range: -4.7098
Max Act: 4.1785. Min Act: -0.1700
Data Index: 5112957 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7098. Min Range: -4.7098
Max Act: 4.1473. Min Act: -0.1700
Data Index: 3590517 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7098. Min Range: -4.7098
Max Act: 4.1473. Min Act: -0.1700
Data Index: 2309047 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7098. Min Range: -4.7098
Max Act: 4.1473. Min Act: -0.1700
Data Index: 7299589 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7098. Min Range: -4.7098
Max Act: 4.1473. Min Act: -0.1700
Data Index: 2547942 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7098. Min Range: -4.7098
Max Act: 4.1160. Min Act: -0.1700
Data Index: 2730501 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #19