Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3054 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9094. Min Range: -7.9094
Max Act: 7.9094. Min Act: -0.1700
Data Index: 5855304 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9094. Min Range: -7.9094
Max Act: 7.9094. Min Act: -0.1700
Data Index: 8806934 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9094. Min Range: -7.9094
Max Act: 7.6907. Min Act: -0.1700
Data Index: 3482063 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9094. Min Range: -7.9094
Max Act: 7.6282. Min Act: -0.1700
Data Index: 2017941 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9094. Min Range: -7.9094
Max Act: 7.5657. Min Act: -0.1700
Data Index: 4072704 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9094. Min Range: -7.9094
Max Act: 7.5032. Min Act: -0.1700
Data Index: 1619159 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9094. Min Range: -7.9094
Max Act: 7.5032. Min Act: -0.1700
Data Index: 8694664 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9094. Min Range: -7.9094
Max Act: 7.5344. Min Act: -0.1700
Data Index: 294984 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9094. Min Range: -7.9094
Max Act: 7.4407. Min Act: -0.1700
Data Index: 4779133 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9094. Min Range: -7.9094
Max Act: 7.4719. Min Act: -0.1700
Data Index: 3752220 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9094. Min Range: -7.9094
Max Act: 7.4094. Min Act: -0.1700
Data Index: 914701 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9094. Min Range: -7.9094
Max Act: 7.4407. Min Act: -0.1700
Data Index: 6060192 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9094. Min Range: -7.9094
Max Act: 7.4407. Min Act: -0.1700
Data Index: 3698053 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9094. Min Range: -7.9094
Max Act: 7.4094. Min Act: -0.1700
Data Index: 7298490 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9094. Min Range: -7.9094
Max Act: 7.4407. Min Act: -0.1700
Data Index: 1554132 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9094. Min Range: -7.9094
Max Act: 7.3782. Min Act: -0.1700
Data Index: 1017518 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9094. Min Range: -7.9094
Max Act: 7.3469. Min Act: -0.1700
Data Index: 7724317 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9094. Min Range: -7.9094
Max Act: 7.3469. Min Act: -0.1700
Data Index: 2162177 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9094. Min Range: -7.9094
Max Act: 7.3469. Min Act: -0.1700
Data Index: 1728322 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9094. Min Range: -7.9094
Max Act: 7.3469. Min Act: -0.1700
Data Index: 8027146 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #19