Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2725 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7810. Min Range: -5.7810
Max Act: 5.7810. Min Act: -0.1700
Data Index: 3657613 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7810. Min Range: -5.7810
Max Act: 5.7185. Min Act: -0.1700
Data Index: 4028649 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7810. Min Range: -5.7810
Max Act: 5.6873. Min Act: -0.1700
Data Index: 4269278 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7810. Min Range: -5.7810
Max Act: 5.7185. Min Act: -0.1700
Data Index: 1622191 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7810. Min Range: -5.7810
Max Act: 5.7185. Min Act: -0.1700
Data Index: 377851 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7810. Min Range: -5.7810
Max Act: 5.6873. Min Act: -0.1700
Data Index: 8338630 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7810. Min Range: -5.7810
Max Act: 5.6560. Min Act: -0.1700
Data Index: 552642 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7810. Min Range: -5.7810
Max Act: 5.6560. Min Act: -0.1700
Data Index: 2163803 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7810. Min Range: -5.7810
Max Act: 5.6248. Min Act: -0.1700
Data Index: 2019528 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7810. Min Range: -5.7810
Max Act: 5.6248. Min Act: -0.1700
Data Index: 5542328 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7810. Min Range: -5.7810
Max Act: 5.6248. Min Act: -0.1700
Data Index: 2398974 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7810. Min Range: -5.7810
Max Act: 5.5935. Min Act: -0.1700
Data Index: 5077294 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7810. Min Range: -5.7810
Max Act: 5.5623. Min Act: -0.1700
Data Index: 940435 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7810. Min Range: -5.7810
Max Act: 5.5935. Min Act: -0.1700
Data Index: 1262874 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7810. Min Range: -5.7810
Max Act: 5.5935. Min Act: -0.1700
Data Index: 3798038 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7810. Min Range: -5.7810
Max Act: 5.5935. Min Act: -0.1700
Data Index: 7421100 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7810. Min Range: -5.7810
Max Act: 5.5935. Min Act: -0.1700
Data Index: 7768417 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7810. Min Range: -5.7810
Max Act: 5.5623. Min Act: -0.1700
Data Index: 801944 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7810. Min Range: -5.7810
Max Act: 5.5623. Min Act: -0.1700
Data Index: 5602781 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7810. Min Range: -5.7810
Max Act: 5.5623. Min Act: -0.1700
Data Index: 5746790 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #19