Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2098 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0573. Min Range: -9.0573
Max Act: 9.0573. Min Act: -0.1700
Data Index: 2513482 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0573. Min Range: -9.0573
Max Act: 9.0573. Min Act: -0.1700
Data Index: 3488237 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0573. Min Range: -9.0573
Max Act: 8.8698. Min Act: -0.1700
Data Index: 276149 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0573. Min Range: -9.0573
Max Act: 8.6823. Min Act: -0.1700
Data Index: 8193258 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0573. Min Range: -9.0573
Max Act: 8.6198. Min Act: -0.1700
Data Index: 2663099 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0573. Min Range: -9.0573
Max Act: 8.6198. Min Act: -0.1700
Data Index: 4909012 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0573. Min Range: -9.0573
Max Act: 8.6198. Min Act: -0.1700
Data Index: 3762657 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0573. Min Range: -9.0573
Max Act: 8.5573. Min Act: -0.1700
Data Index: 4668691 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0573. Min Range: -9.0573
Max Act: 8.5573. Min Act: -0.1700
Data Index: 7424605 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0573. Min Range: -9.0573
Max Act: 8.5573. Min Act: -0.1700
Data Index: 3317992 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0573. Min Range: -9.0573
Max Act: 8.4948. Min Act: -0.1700
Data Index: 3689238 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0573. Min Range: -9.0573
Max Act: 8.4948. Min Act: -0.1700
Data Index: 7528553 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0573. Min Range: -9.0573
Max Act: 8.4948. Min Act: -0.1700
Data Index: 5318041 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0573. Min Range: -9.0573
Max Act: 8.4948. Min Act: -0.1700
Data Index: 5340890 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0573. Min Range: -9.0573
Max Act: 8.4948. Min Act: -0.1700
Data Index: 7620731 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0573. Min Range: -9.0573
Max Act: 8.4323. Min Act: -0.1700
Data Index: 5239873 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0573. Min Range: -9.0573
Max Act: 8.4323. Min Act: -0.1700
Data Index: 4663731 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0573. Min Range: -9.0573
Max Act: 8.4323. Min Act: -0.1700
Data Index: 6770943 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0573. Min Range: -9.0573
Max Act: 8.4323. Min Act: -0.1700
Data Index: 2377090 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0573. Min Range: -9.0573
Max Act: 8.3698. Min Act: -0.1700
Data Index: 355610 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #19