Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2651 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1816. Min Range: -9.1816
Max Act: 9.1816. Min Act: -0.1700
Data Index: 3834860 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1816. Min Range: -9.1816
Max Act: 8.6816. Min Act: -0.1700
Data Index: 1028852 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1816. Min Range: -9.1816
Max Act: 8.6816. Min Act: -0.1700
Data Index: 4029665 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1816. Min Range: -9.1816
Max Act: 8.5566. Min Act: -0.1700
Data Index: 2090465 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1816. Min Range: -9.1816
Max Act: 8.4316. Min Act: -0.1700
Data Index: 1106972 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1816. Min Range: -9.1816
Max Act: 8.4316. Min Act: -0.1700
Data Index: 2760689 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1816. Min Range: -9.1816
Max Act: 8.3691. Min Act: -0.1700
Data Index: 5443338 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1816. Min Range: -9.1816
Max Act: 8.3066. Min Act: -0.1700
Data Index: 2427388 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1816. Min Range: -9.1816
Max Act: 8.2441. Min Act: -0.1700
Data Index: 1028849 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1816. Min Range: -9.1816
Max Act: 8.2441. Min Act: -0.1700
Data Index: 4422449 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1816. Min Range: -9.1816
Max Act: 8.2441. Min Act: -0.1700
Data Index: 6974025 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1816. Min Range: -9.1816
Max Act: 8.1816. Min Act: -0.1700
Data Index: 1028851 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1816. Min Range: -9.1816
Max Act: 8.2441. Min Act: -0.1700
Data Index: 5189160 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1816. Min Range: -9.1816
Max Act: 8.1191. Min Act: -0.1700
Data Index: 69730 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1816. Min Range: -9.1816
Max Act: 8.1191. Min Act: -0.1700
Data Index: 1393640 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1816. Min Range: -9.1816
Max Act: 8.0566. Min Act: -0.1700
Data Index: 3265695 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1816. Min Range: -9.1816
Max Act: 8.0566. Min Act: -0.1700
Data Index: 1591014 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1816. Min Range: -9.1816
Max Act: 8.0566. Min Act: -0.1700
Data Index: 6303999 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1816. Min Range: -9.1816
Max Act: 8.0566. Min Act: -0.1700
Data Index: 759391 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1816. Min Range: -9.1816
Max Act: 8.1191. Min Act: -0.1700
Data Index: 4029653 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #19