Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4391 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8277. Min Range: -7.8277
Max Act: 7.8277. Min Act: -0.1700
Data Index: 567526 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8277. Min Range: -7.8277
Max Act: 7.7027. Min Act: -0.1700
Data Index: 4993367 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8277. Min Range: -7.8277
Max Act: 7.6402. Min Act: -0.1700
Data Index: 5494604 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8277. Min Range: -7.8277
Max Act: 7.6402. Min Act: -0.1700
Data Index: 8290387 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8277. Min Range: -7.8277
Max Act: 7.3589. Min Act: -0.1700
Data Index: 2596048 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8277. Min Range: -7.8277
Max Act: 7.2652. Min Act: -0.1700
Data Index: 7709514 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8277. Min Range: -7.8277
Max Act: 7.2339. Min Act: -0.1700
Data Index: 382121 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8277. Min Range: -7.8277
Max Act: 7.2027. Min Act: -0.1700
Data Index: 3224880 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8277. Min Range: -7.8277
Max Act: 7.1402. Min Act: -0.1700
Data Index: 3379585 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8277. Min Range: -7.8277
Max Act: 7.1714. Min Act: -0.1700
Data Index: 4616181 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8277. Min Range: -7.8277
Max Act: 7.1714. Min Act: -0.1700
Data Index: 719083 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8277. Min Range: -7.8277
Max Act: 7.1089. Min Act: -0.1700
Data Index: 8128218 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8277. Min Range: -7.8277
Max Act: 7.0777. Min Act: -0.1700
Data Index: 2995496 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8277. Min Range: -7.8277
Max Act: 6.9527. Min Act: -0.1700
Data Index: 8806886 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8277. Min Range: -7.8277
Max Act: 6.8589. Min Act: -0.1700
Data Index: 4921869 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8277. Min Range: -7.8277
Max Act: 6.8589. Min Act: -0.1700
Data Index: 6079110 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8277. Min Range: -7.8277
Max Act: 6.7964. Min Act: -0.1700
Data Index: 4949003 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8277. Min Range: -7.8277
Max Act: 6.8277. Min Act: -0.1700
Data Index: 937779 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8277. Min Range: -7.8277
Max Act: 6.7964. Min Act: -0.1700
Data Index: 587761 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8277. Min Range: -7.8277
Max Act: 6.7964. Min Act: -0.1700
Data Index: 4709173 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #19