Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 214 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4240. Min Range: -6.4240
Max Act: 6.4240. Min Act: -0.1700
Data Index: 8113760 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4240. Min Range: -6.4240
Max Act: 6.4240. Min Act: -0.1700
Data Index: 4948907 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4240. Min Range: -6.4240
Max Act: 6.2990. Min Act: -0.1700
Data Index: 2275326 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4240. Min Range: -6.4240
Max Act: 6.2678. Min Act: -0.1700
Data Index: 520109 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4240. Min Range: -6.4240
Max Act: 6.1740. Min Act: -0.1700
Data Index: 7008626 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4240. Min Range: -6.4240
Max Act: 6.1115. Min Act: -0.1700
Data Index: 4337796 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4240. Min Range: -6.4240
Max Act: 6.0490. Min Act: -0.1700
Data Index: 6734019 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4240. Min Range: -6.4240
Max Act: 6.0490. Min Act: -0.1700
Data Index: 3122915 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4240. Min Range: -6.4240
Max Act: 6.0803. Min Act: -0.1700
Data Index: 8291191 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4240. Min Range: -6.4240
Max Act: 6.0490. Min Act: -0.1700
Data Index: 6555787 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4240. Min Range: -6.4240
Max Act: 6.0803. Min Act: -0.1700
Data Index: 4832626 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4240. Min Range: -6.4240
Max Act: 6.0490. Min Act: -0.1700
Data Index: 7783520 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4240. Min Range: -6.4240
Max Act: 5.9865. Min Act: -0.1700
Data Index: 565206 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4240. Min Range: -6.4240
Max Act: 5.9865. Min Act: -0.1700
Data Index: 5730207 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4240. Min Range: -6.4240
Max Act: 5.9553. Min Act: -0.1700
Data Index: 8713910 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4240. Min Range: -6.4240
Max Act: 5.9553. Min Act: -0.1700
Data Index: 8384659 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4240. Min Range: -6.4240
Max Act: 5.9553. Min Act: -0.1700
Data Index: 3226184 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4240. Min Range: -6.4240
Max Act: 5.9553. Min Act: -0.1700
Data Index: 2242520 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4240. Min Range: -6.4240
Max Act: 5.9240. Min Act: -0.1700
Data Index: 90776 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4240. Min Range: -6.4240
Max Act: 5.9240. Min Act: -0.1700
Data Index: 5985176 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #19