Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2994 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4740. Min Range: -5.4740
Max Act: 5.4740. Min Act: -0.1700
Data Index: 601034 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4740. Min Range: -5.4740
Max Act: 5.0990. Min Act: -0.1700
Data Index: 3665398 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4740. Min Range: -5.4740
Max Act: 5.0678. Min Act: -0.1700
Data Index: 7238371 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4740. Min Range: -5.4740
Max Act: 5.0365. Min Act: -0.1700
Data Index: 4007950 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4740. Min Range: -5.4740
Max Act: 5.0053. Min Act: -0.1700
Data Index: 6810265 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4740. Min Range: -5.4740
Max Act: 4.9740. Min Act: -0.1700
Data Index: 8698039 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4740. Min Range: -5.4740
Max Act: 4.9428. Min Act: -0.1700
Data Index: 3533050 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4740. Min Range: -5.4740
Max Act: 4.9115. Min Act: -0.1700
Data Index: 816486 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4740. Min Range: -5.4740
Max Act: 4.9115. Min Act: -0.1700
Data Index: 1735914 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4740. Min Range: -5.4740
Max Act: 4.9115. Min Act: -0.1700
Data Index: 6216488 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4740. Min Range: -5.4740
Max Act: 4.8803. Min Act: -0.1700
Data Index: 6727751 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4740. Min Range: -5.4740
Max Act: 4.8803. Min Act: -0.1700
Data Index: 7926149 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4740. Min Range: -5.4740
Max Act: 4.9115. Min Act: -0.1700
Data Index: 4298654 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4740. Min Range: -5.4740
Max Act: 4.8803. Min Act: -0.1700
Data Index: 8471872 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4740. Min Range: -5.4740
Max Act: 4.8490. Min Act: -0.1700
Data Index: 8071949 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4740. Min Range: -5.4740
Max Act: 4.8178. Min Act: -0.1700
Data Index: 1891911 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4740. Min Range: -5.4740
Max Act: 4.7865. Min Act: -0.1700
Data Index: 829880 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4740. Min Range: -5.4740
Max Act: 4.7865. Min Act: -0.1700
Data Index: 6408627 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4740. Min Range: -5.4740
Max Act: 4.7865. Min Act: -0.1700
Data Index: 3013783 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4740. Min Range: -5.4740
Max Act: 4.7240. Min Act: -0.1700
Data Index: 427776 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #19