Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3484 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7348. Min Range: -6.7348
Max Act: 6.7348. Min Act: -0.1700
Data Index: 1686372 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7348. Min Range: -6.7348
Max Act: 6.7348. Min Act: -0.1700
Data Index: 473394 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7348. Min Range: -6.7348
Max Act: 6.4536. Min Act: -0.1700
Data Index: 8568959 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7348. Min Range: -6.7348
Max Act: 6.3911. Min Act: -0.1700
Data Index: 206749 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7348. Min Range: -6.7348
Max Act: 6.3286. Min Act: -0.1700
Data Index: 1655220 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7348. Min Range: -6.7348
Max Act: 6.2973. Min Act: -0.1700
Data Index: 4617316 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7348. Min Range: -6.7348
Max Act: 6.2973. Min Act: -0.1700
Data Index: 396351 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7348. Min Range: -6.7348
Max Act: 6.2973. Min Act: -0.1700
Data Index: 5252641 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7348. Min Range: -6.7348
Max Act: 6.2661. Min Act: -0.1700
Data Index: 4872430 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7348. Min Range: -6.7348
Max Act: 6.2348. Min Act: -0.1700
Data Index: 4154644 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7348. Min Range: -6.7348
Max Act: 6.2036. Min Act: -0.1700
Data Index: 2045470 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7348. Min Range: -6.7348
Max Act: 6.2036. Min Act: -0.1700
Data Index: 4962433 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7348. Min Range: -6.7348
Max Act: 6.1723. Min Act: -0.1700
Data Index: 7984597 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7348. Min Range: -6.7348
Max Act: 6.1723. Min Act: -0.1700
Data Index: 4003359 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7348. Min Range: -6.7348
Max Act: 6.1723. Min Act: -0.1700
Data Index: 5213194 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7348. Min Range: -6.7348
Max Act: 6.1723. Min Act: -0.1700
Data Index: 162305 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7348. Min Range: -6.7348
Max Act: 6.1723. Min Act: -0.1700
Data Index: 3518943 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7348. Min Range: -6.7348
Max Act: 6.1411. Min Act: -0.1700
Data Index: 4878593 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7348. Min Range: -6.7348
Max Act: 6.1411. Min Act: -0.1700
Data Index: 2107797 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7348. Min Range: -6.7348
Max Act: 6.1098. Min Act: -0.1700
Data Index: 1320438 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #19