Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1706 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6964. Min Range: -6.6964
Max Act: 6.6964. Min Act: -0.1700
Data Index: 4581703 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6964. Min Range: -6.6964
Max Act: 6.4464. Min Act: -0.1700
Data Index: 637508 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6964. Min Range: -6.6964
Max Act: 6.4464. Min Act: -0.1700
Data Index: 8301787 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6964. Min Range: -6.6964
Max Act: 6.4464. Min Act: -0.1700
Data Index: 5677659 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6964. Min Range: -6.6964
Max Act: 6.4464. Min Act: -0.1700
Data Index: 5236393 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6964. Min Range: -6.6964
Max Act: 6.4152. Min Act: -0.1700
Data Index: 4622485 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6964. Min Range: -6.6964
Max Act: 6.3527. Min Act: -0.1700
Data Index: 8054153 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6964. Min Range: -6.6964
Max Act: 6.3527. Min Act: -0.1700
Data Index: 7477755 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6964. Min Range: -6.6964
Max Act: 6.3527. Min Act: -0.1700
Data Index: 2012201 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6964. Min Range: -6.6964
Max Act: 6.2902. Min Act: -0.1700
Data Index: 3427968 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6964. Min Range: -6.6964
Max Act: 6.2589. Min Act: -0.1700
Data Index: 8508880 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6964. Min Range: -6.6964
Max Act: 6.2589. Min Act: -0.1700
Data Index: 1423 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6964. Min Range: -6.6964
Max Act: 6.2277. Min Act: -0.1700
Data Index: 5252692 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6964. Min Range: -6.6964
Max Act: 6.2277. Min Act: -0.1700
Data Index: 968928 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6964. Min Range: -6.6964
Max Act: 6.2277. Min Act: -0.1700
Data Index: 1002216 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6964. Min Range: -6.6964
Max Act: 6.1964. Min Act: -0.1700
Data Index: 7448646 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6964. Min Range: -6.6964
Max Act: 6.1964. Min Act: -0.1700
Data Index: 2293660 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6964. Min Range: -6.6964
Max Act: 6.1652. Min Act: -0.1700
Data Index: 2751163 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6964. Min Range: -6.6964
Max Act: 6.1652. Min Act: -0.1700
Data Index: 4308381 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6964. Min Range: -6.6964
Max Act: 6.1339. Min Act: -0.1700
Data Index: 2738389 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #19