Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3989 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4610. Min Range: -3.4610
Max Act: 3.4610. Min Act: -0.1700
Data Index: 3296028 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4610. Min Range: -3.4610
Max Act: 3.4296. Min Act: -0.1700
Data Index: 2607350 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4610. Min Range: -3.4610
Max Act: 3.3356. Min Act: -0.1700
Data Index: 5789953 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4610. Min Range: -3.4610
Max Act: 3.3042. Min Act: -0.1700
Data Index: 230618 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4610. Min Range: -3.4610
Max Act: 3.2885. Min Act: -0.1700
Data Index: 3523630 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4610. Min Range: -3.4610
Max Act: 3.2885. Min Act: -0.1700
Data Index: 326339 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4610. Min Range: -3.4610
Max Act: 3.2728. Min Act: -0.1700
Data Index: 2634847 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4610. Min Range: -3.4610
Max Act: 3.2571. Min Act: -0.1700
Data Index: 8830968 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4610. Min Range: -3.4610
Max Act: 3.2728. Min Act: -0.1700
Data Index: 3710433 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4610. Min Range: -3.4610
Max Act: 3.2885. Min Act: -0.1700
Data Index: 7265224 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4610. Min Range: -3.4610
Max Act: 3.2571. Min Act: -0.1700
Data Index: 1974489 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4610. Min Range: -3.4610
Max Act: 3.2571. Min Act: -0.1700
Data Index: 124981 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4610. Min Range: -3.4610
Max Act: 3.2571. Min Act: -0.1700
Data Index: 8148230 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4610. Min Range: -3.4610
Max Act: 3.2413. Min Act: -0.1700
Data Index: 5379387 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4610. Min Range: -3.4610
Max Act: 3.2413. Min Act: -0.1700
Data Index: 4709632 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4610. Min Range: -3.4610
Max Act: 3.2413. Min Act: -0.1700
Data Index: 3739259 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4610. Min Range: -3.4610
Max Act: 3.2413. Min Act: -0.1700
Data Index: 1120316 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4610. Min Range: -3.4610
Max Act: 3.2256. Min Act: -0.1700
Data Index: 3997119 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4610. Min Range: -3.4610
Max Act: 3.2256. Min Act: -0.1700
Data Index: 280884 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4610. Min Range: -3.4610
Max Act: 3.2256. Min Act: -0.1700
Data Index: 7687433 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #19