Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3640 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4886. Min Range: -4.4886
Max Act: 4.4886. Min Act: -0.1700
Data Index: 6847895 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4886. Min Range: -4.4886
Max Act: 4.3323. Min Act: -0.1700
Data Index: 7323529 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4886. Min Range: -4.4886
Max Act: 4.2386. Min Act: -0.1700
Data Index: 549265 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4886. Min Range: -4.4886
Max Act: 4.2073. Min Act: -0.1700
Data Index: 6096978 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4886. Min Range: -4.4886
Max Act: 4.2073. Min Act: -0.1700
Data Index: 6435286 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4886. Min Range: -4.4886
Max Act: 4.1761. Min Act: -0.1700
Data Index: 2303869 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4886. Min Range: -4.4886
Max Act: 4.1448. Min Act: -0.1700
Data Index: 8386313 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4886. Min Range: -4.4886
Max Act: 4.1448. Min Act: -0.1700
Data Index: 164342 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4886. Min Range: -4.4886
Max Act: 4.1761. Min Act: -0.1700
Data Index: 804012 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4886. Min Range: -4.4886
Max Act: 4.0823. Min Act: -0.1700
Data Index: 4866540 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4886. Min Range: -4.4886
Max Act: 4.0510. Min Act: -0.1700
Data Index: 2946862 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4886. Min Range: -4.4886
Max Act: 4.0510. Min Act: -0.1700
Data Index: 4468097 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4886. Min Range: -4.4886
Max Act: 4.0510. Min Act: -0.1700
Data Index: 870178 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4886. Min Range: -4.4886
Max Act: 4.0510. Min Act: -0.1700
Data Index: 6744226 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4886. Min Range: -4.4886
Max Act: 4.0198. Min Act: -0.1700
Data Index: 6725788 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4886. Min Range: -4.4886
Max Act: 3.9885. Min Act: -0.1700
Data Index: 2721319 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4886. Min Range: -4.4886
Max Act: 3.9885. Min Act: -0.1700
Data Index: 3309252 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4886. Min Range: -4.4886
Max Act: 3.9885. Min Act: -0.1700
Data Index: 8726364 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4886. Min Range: -4.4886
Max Act: 3.9885. Min Act: -0.1700
Data Index: 6991425 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4886. Min Range: -4.4886
Max Act: 3.9885. Min Act: -0.1700
Data Index: 2986956 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #19