Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3256 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6402. Min Range: -5.6402
Max Act: 5.6402. Min Act: -0.1700
Data Index: 5750190 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6402. Min Range: -5.6402
Max Act: 5.4527. Min Act: -0.1700
Data Index: 1067603 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6402. Min Range: -5.6402
Max Act: 5.4527. Min Act: -0.1700
Data Index: 8525649 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6402. Min Range: -5.6402
Max Act: 5.4527. Min Act: -0.1700
Data Index: 8525651 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6402. Min Range: -5.6402
Max Act: 5.4214. Min Act: -0.1700
Data Index: 2389712 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6402. Min Range: -5.6402
Max Act: 5.3902. Min Act: -0.1700
Data Index: 8387574 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6402. Min Range: -5.6402
Max Act: 5.3589. Min Act: -0.1700
Data Index: 2632105 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6402. Min Range: -5.6402
Max Act: 5.3589. Min Act: -0.1700
Data Index: 8413792 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6402. Min Range: -5.6402
Max Act: 5.3589. Min Act: -0.1700
Data Index: 4537165 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6402. Min Range: -5.6402
Max Act: 5.3589. Min Act: -0.1700
Data Index: 4851023 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6402. Min Range: -5.6402
Max Act: 5.2964. Min Act: -0.1700
Data Index: 3583605 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6402. Min Range: -5.6402
Max Act: 5.3277. Min Act: -0.1700
Data Index: 7865806 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6402. Min Range: -5.6402
Max Act: 5.3277. Min Act: -0.1700
Data Index: 8413791 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6402. Min Range: -5.6402
Max Act: 5.3589. Min Act: -0.1700
Data Index: 7436458 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6402. Min Range: -5.6402
Max Act: 5.3277. Min Act: -0.1700
Data Index: 7252505 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6402. Min Range: -5.6402
Max Act: 5.2964. Min Act: -0.1700
Data Index: 5404942 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6402. Min Range: -5.6402
Max Act: 5.2964. Min Act: -0.1700
Data Index: 6793350 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6402. Min Range: -5.6402
Max Act: 5.2964. Min Act: -0.1700
Data Index: 766314 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6402. Min Range: -5.6402
Max Act: 5.2652. Min Act: -0.1700
Data Index: 4476726 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6402. Min Range: -5.6402
Max Act: 5.2339. Min Act: -0.1700
Data Index: 5717576 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #19