Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 818 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2658. Min Range: -6.2658
Max Act: 6.2658. Min Act: -0.1700
Data Index: 8645473 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2658. Min Range: -6.2658
Max Act: 6.0783. Min Act: -0.1700
Data Index: 5130502 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2658. Min Range: -6.2658
Max Act: 6.0158. Min Act: -0.1700
Data Index: 6353215 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2658. Min Range: -6.2658
Max Act: 5.8908. Min Act: -0.1700
Data Index: 6024092 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2658. Min Range: -6.2658
Max Act: 5.8283. Min Act: -0.1700
Data Index: 880264 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2658. Min Range: -6.2658
Max Act: 5.7971. Min Act: -0.1700
Data Index: 857621 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2658. Min Range: -6.2658
Max Act: 5.7658. Min Act: -0.1700
Data Index: 6994499 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2658. Min Range: -6.2658
Max Act: 5.7658. Min Act: -0.1700
Data Index: 294304 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2658. Min Range: -6.2658
Max Act: 5.7658. Min Act: -0.1700
Data Index: 8135701 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2658. Min Range: -6.2658
Max Act: 5.7346. Min Act: -0.1700
Data Index: 146193 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2658. Min Range: -6.2658
Max Act: 5.7346. Min Act: -0.1700
Data Index: 6682739 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2658. Min Range: -6.2658
Max Act: 5.7346. Min Act: -0.1700
Data Index: 2036305 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2658. Min Range: -6.2658
Max Act: 5.7033. Min Act: -0.1700
Data Index: 606461 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2658. Min Range: -6.2658
Max Act: 5.6721. Min Act: -0.1700
Data Index: 2227294 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2658. Min Range: -6.2658
Max Act: 5.6408. Min Act: -0.1700
Data Index: 3525920 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2658. Min Range: -6.2658
Max Act: 5.6408. Min Act: -0.1700
Data Index: 5580471 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2658. Min Range: -6.2658
Max Act: 5.6721. Min Act: -0.1700
Data Index: 3989714 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2658. Min Range: -6.2658
Max Act: 5.6096. Min Act: -0.1700
Data Index: 5701293 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2658. Min Range: -6.2658
Max Act: 5.6096. Min Act: -0.1700
Data Index: 879257 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2658. Min Range: -6.2658
Max Act: 5.6096. Min Act: -0.1700
Data Index: 4073288 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #19