Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3521 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7389. Min Range: -5.7389
Max Act: 5.7389. Min Act: -0.1700
Data Index: 8196836 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7389. Min Range: -5.7389
Max Act: 5.6451. Min Act: -0.1700
Data Index: 7005289 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7389. Min Range: -5.7389
Max Act: 5.5826. Min Act: -0.1700
Data Index: 6478914 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7389. Min Range: -5.7389
Max Act: 5.5514. Min Act: -0.1700
Data Index: 2746123 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7389. Min Range: -5.7389
Max Act: 5.5201. Min Act: -0.1700
Data Index: 6211066 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7389. Min Range: -5.7389
Max Act: 5.5201. Min Act: -0.1700
Data Index: 7290919 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7389. Min Range: -5.7389
Max Act: 5.4889. Min Act: -0.1700
Data Index: 516044 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7389. Min Range: -5.7389
Max Act: 5.4889. Min Act: -0.1700
Data Index: 8352305 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7389. Min Range: -5.7389
Max Act: 5.4576. Min Act: -0.1700
Data Index: 6211068 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7389. Min Range: -5.7389
Max Act: 5.4889. Min Act: -0.1700
Data Index: 6211076 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7389. Min Range: -5.7389
Max Act: 5.4576. Min Act: -0.1700
Data Index: 2948902 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7389. Min Range: -5.7389
Max Act: 5.4576. Min Act: -0.1700
Data Index: 5673176 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7389. Min Range: -5.7389
Max Act: 5.4576. Min Act: -0.1700
Data Index: 4386118 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7389. Min Range: -5.7389
Max Act: 5.4264. Min Act: -0.1700
Data Index: 326153 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7389. Min Range: -5.7389
Max Act: 5.4576. Min Act: -0.1700
Data Index: 5782540 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7389. Min Range: -5.7389
Max Act: 5.4264. Min Act: -0.1700
Data Index: 4272884 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7389. Min Range: -5.7389
Max Act: 5.4264. Min Act: -0.1700
Data Index: 4700246 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7389. Min Range: -5.7389
Max Act: 5.4264. Min Act: -0.1700
Data Index: 6111251 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7389. Min Range: -5.7389
Max Act: 5.3951. Min Act: -0.1700
Data Index: 7383174 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7389. Min Range: -5.7389
Max Act: 5.3951. Min Act: -0.1700
Data Index: 6314053 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #19