Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3063 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3303. Min Range: -7.3303
Max Act: 7.3303. Min Act: -0.1700
Data Index: 5701382 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3303. Min Range: -7.3303
Max Act: 6.2053. Min Act: -0.1700
Data Index: 5732772 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3303. Min Range: -7.3303
Max Act: 6.1428. Min Act: -0.1700
Data Index: 2760581 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3303. Min Range: -7.3303
Max Act: 5.9865. Min Act: -0.1700
Data Index: 1593347 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3303. Min Range: -7.3303
Max Act: 5.9865. Min Act: -0.1700
Data Index: 3154449 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3303. Min Range: -7.3303
Max Act: 5.9553. Min Act: -0.1700
Data Index: 6136371 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3303. Min Range: -7.3303
Max Act: 5.9240. Min Act: -0.1700
Data Index: 4529453 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3303. Min Range: -7.3303
Max Act: 5.9553. Min Act: -0.1700
Data Index: 2136154 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3303. Min Range: -7.3303
Max Act: 5.9240. Min Act: -0.1700
Data Index: 4106441 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3303. Min Range: -7.3303
Max Act: 5.9240. Min Act: -0.1700
Data Index: 2403950 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3303. Min Range: -7.3303
Max Act: 5.8615. Min Act: -0.1700
Data Index: 4684199 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3303. Min Range: -7.3303
Max Act: 5.8928. Min Act: -0.1700
Data Index: 8117119 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3303. Min Range: -7.3303
Max Act: 5.8303. Min Act: -0.1700
Data Index: 5648402 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3303. Min Range: -7.3303
Max Act: 5.8303. Min Act: -0.1700
Data Index: 2704313 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3303. Min Range: -7.3303
Max Act: 5.8303. Min Act: -0.1700
Data Index: 2066459 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3303. Min Range: -7.3303
Max Act: 5.8303. Min Act: -0.1700
Data Index: 3271097 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3303. Min Range: -7.3303
Max Act: 5.7990. Min Act: -0.1700
Data Index: 7518757 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3303. Min Range: -7.3303
Max Act: 5.8303. Min Act: -0.1700
Data Index: 5602339 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3303. Min Range: -7.3303
Max Act: 5.7990. Min Act: -0.1700
Data Index: 3454931 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3303. Min Range: -7.3303
Max Act: 5.7678. Min Act: -0.1700
Data Index: 27671 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #19