Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1969 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6593. Min Range: -9.6593
Max Act: 9.6593. Min Act: -0.1700
Data Index: 1477123 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6593. Min Range: -9.6593
Max Act: 9.5343. Min Act: -0.1700
Data Index: 276289 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6593. Min Range: -9.6593
Max Act: 9.4093. Min Act: -0.1700
Data Index: 1542735 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6593. Min Range: -9.6593
Max Act: 9.4093. Min Act: -0.1700
Data Index: 1920566 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6593. Min Range: -9.6593
Max Act: 8.7843. Min Act: -0.1700
Data Index: 3259612 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6593. Min Range: -9.6593
Max Act: 8.3468. Min Act: -0.1700
Data Index: 6344379 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6593. Min Range: -9.6593
Max Act: 8.1905. Min Act: -0.1700
Data Index: 4920729 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6593. Min Range: -9.6593
Max Act: 8.2218. Min Act: -0.1700
Data Index: 3477753 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6593. Min Range: -9.6593
Max Act: 8.1905. Min Act: -0.1700
Data Index: 4553428 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6593. Min Range: -9.6593
Max Act: 8.1593. Min Act: -0.1700
Data Index: 5129040 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6593. Min Range: -9.6593
Max Act: 8.1905. Min Act: -0.1700
Data Index: 6982073 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6593. Min Range: -9.6593
Max Act: 8.1280. Min Act: -0.1700
Data Index: 6440513 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6593. Min Range: -9.6593
Max Act: 8.1280. Min Act: -0.1700
Data Index: 896239 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6593. Min Range: -9.6593
Max Act: 8.0968. Min Act: -0.1700
Data Index: 7095461 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6593. Min Range: -9.6593
Max Act: 8.0655. Min Act: -0.1700
Data Index: 3235114 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6593. Min Range: -9.6593
Max Act: 8.0343. Min Act: -0.1700
Data Index: 6865255 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6593. Min Range: -9.6593
Max Act: 8.0655. Min Act: -0.1700
Data Index: 1193767 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6593. Min Range: -9.6593
Max Act: 8.0030. Min Act: -0.1700
Data Index: 6441966 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6593. Min Range: -9.6593
Max Act: 8.0030. Min Act: -0.1700
Data Index: 3682357 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6593. Min Range: -9.6593
Max Act: 7.9718. Min Act: -0.1700
Data Index: 5188626 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #19