Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1629 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5033. Min Range: -4.5033
Max Act: 4.5033. Min Act: -0.1700
Data Index: 2653165 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5033. Min Range: -4.5033
Max Act: 4.4096. Min Act: -0.1700
Data Index: 8801049 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5033. Min Range: -4.5033
Max Act: 4.4408. Min Act: -0.1700
Data Index: 1253209 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5033. Min Range: -4.5033
Max Act: 4.3471. Min Act: -0.1700
Data Index: 7606700 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5033. Min Range: -4.5033
Max Act: 4.2846. Min Act: -0.1700
Data Index: 906916 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5033. Min Range: -4.5033
Max Act: 4.2533. Min Act: -0.1700
Data Index: 6504058 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5033. Min Range: -4.5033
Max Act: 4.2533. Min Act: -0.1700
Data Index: 5201732 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5033. Min Range: -4.5033
Max Act: 4.2221. Min Act: -0.1700
Data Index: 3362819 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5033. Min Range: -4.5033
Max Act: 4.2221. Min Act: -0.1700
Data Index: 4806633 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5033. Min Range: -4.5033
Max Act: 4.1908. Min Act: -0.1700
Data Index: 2795413 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5033. Min Range: -4.5033
Max Act: 4.1908. Min Act: -0.1700
Data Index: 4290211 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5033. Min Range: -4.5033
Max Act: 4.1908. Min Act: -0.1700
Data Index: 4734946 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5033. Min Range: -4.5033
Max Act: 4.1596. Min Act: -0.1700
Data Index: 3054830 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5033. Min Range: -4.5033
Max Act: 4.1283. Min Act: -0.1700
Data Index: 5682033 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5033. Min Range: -4.5033
Max Act: 4.1283. Min Act: -0.1700
Data Index: 1060727 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5033. Min Range: -4.5033
Max Act: 4.1283. Min Act: -0.1700
Data Index: 2556495 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5033. Min Range: -4.5033
Max Act: 4.1283. Min Act: -0.1700
Data Index: 6179375 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5033. Min Range: -4.5033
Max Act: 4.0971. Min Act: -0.1700
Data Index: 1025974 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5033. Min Range: -4.5033
Max Act: 4.0971. Min Act: -0.1700
Data Index: 5591170 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5033. Min Range: -4.5033
Max Act: 4.0971. Min Act: -0.1700
Data Index: 5029504 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #19