Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3825 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4997. Min Range: -5.4997
Max Act: 5.4997. Min Act: -0.1700
Data Index: 1536057 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4997. Min Range: -5.4997
Max Act: 5.4060. Min Act: -0.1700
Data Index: 6704244 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4997. Min Range: -5.4997
Max Act: 5.4060. Min Act: -0.1700
Data Index: 3089811 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4997. Min Range: -5.4997
Max Act: 5.3435. Min Act: -0.1700
Data Index: 4670205 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4997. Min Range: -5.4997
Max Act: 5.3435. Min Act: -0.1700
Data Index: 2396906 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4997. Min Range: -5.4997
Max Act: 5.3435. Min Act: -0.1700
Data Index: 610504 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4997. Min Range: -5.4997
Max Act: 5.3435. Min Act: -0.1700
Data Index: 2154004 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4997. Min Range: -5.4997
Max Act: 5.3122. Min Act: -0.1700
Data Index: 3326792 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4997. Min Range: -5.4997
Max Act: 5.2810. Min Act: -0.1700
Data Index: 5877738 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4997. Min Range: -5.4997
Max Act: 5.2810. Min Act: -0.1700
Data Index: 3427815 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4997. Min Range: -5.4997
Max Act: 5.2497. Min Act: -0.1700
Data Index: 938053 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4997. Min Range: -5.4997
Max Act: 5.2185. Min Act: -0.1700
Data Index: 7195068 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4997. Min Range: -5.4997
Max Act: 5.2497. Min Act: -0.1700
Data Index: 859308 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4997. Min Range: -5.4997
Max Act: 5.2185. Min Act: -0.1700
Data Index: 8087023 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4997. Min Range: -5.4997
Max Act: 5.2185. Min Act: -0.1700
Data Index: 7738327 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4997. Min Range: -5.4997
Max Act: 5.1872. Min Act: -0.1700
Data Index: 1442348 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4997. Min Range: -5.4997
Max Act: 5.1560. Min Act: -0.1700
Data Index: 2204086 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4997. Min Range: -5.4997
Max Act: 5.1872. Min Act: -0.1700
Data Index: 2612038 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4997. Min Range: -5.4997
Max Act: 5.1872. Min Act: -0.1700
Data Index: 7276456 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4997. Min Range: -5.4997
Max Act: 5.1872. Min Act: -0.1700
Data Index: 5394490 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #19