Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1871 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.3075. Min Range: -11.3075
Max Act: 11.3075. Min Act: -0.1700
Data Index: 4590888 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.3075. Min Range: -11.3075
Max Act: 10.5575. Min Act: -0.1700
Data Index: 8093722 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.3075. Min Range: -11.3075
Max Act: 9.9950. Min Act: -0.1700
Data Index: 4160081 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.3075. Min Range: -11.3075
Max Act: 9.8075. Min Act: -0.1700
Data Index: 6636325 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.3075. Min Range: -11.3075
Max Act: 9.6825. Min Act: -0.1700
Data Index: 8783068 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.3075. Min Range: -11.3075
Max Act: 9.5575. Min Act: -0.1700
Data Index: 7939862 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.3075. Min Range: -11.3075
Max Act: 9.5575. Min Act: -0.1700
Data Index: 1100153 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.3075. Min Range: -11.3075
Max Act: 9.4950. Min Act: -0.1700
Data Index: 1586825 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.3075. Min Range: -11.3075
Max Act: 9.4325. Min Act: -0.1700
Data Index: 2334207 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.3075. Min Range: -11.3075
Max Act: 9.4325. Min Act: -0.1700
Data Index: 297693 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.3075. Min Range: -11.3075
Max Act: 9.4325. Min Act: -0.1700
Data Index: 3721063 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.3075. Min Range: -11.3075
Max Act: 9.3700. Min Act: -0.1700
Data Index: 1543000 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.3075. Min Range: -11.3075
Max Act: 9.3700. Min Act: -0.1700
Data Index: 690547 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.3075. Min Range: -11.3075
Max Act: 9.3075. Min Act: -0.1700
Data Index: 6655824 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.3075. Min Range: -11.3075
Max Act: 9.3075. Min Act: -0.1700
Data Index: 4997439 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.3075. Min Range: -11.3075
Max Act: 9.3075. Min Act: -0.1700
Data Index: 6471816 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.3075. Min Range: -11.3075
Max Act: 9.3075. Min Act: -0.1700
Data Index: 2130242 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.3075. Min Range: -11.3075
Max Act: 9.3075. Min Act: -0.1700
Data Index: 6198027 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.3075. Min Range: -11.3075
Max Act: 9.2450. Min Act: -0.1700
Data Index: 4382548 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.3075. Min Range: -11.3075
Max Act: 9.2450. Min Act: -0.1700
Data Index: 658254 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #19