Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2639 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1674. Min Range: -7.1674
Max Act: 7.1674. Min Act: -0.1700
Data Index: 7969477 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1674. Min Range: -7.1674
Max Act: 7.0112. Min Act: -0.1698
Data Index: 4573346 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1674. Min Range: -7.1674
Max Act: 6.8549. Min Act: -0.1700
Data Index: 4158711 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1674. Min Range: -7.1674
Max Act: 6.8237. Min Act: -0.1700
Data Index: 4039529 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1674. Min Range: -7.1674
Max Act: 6.8237. Min Act: -0.1700
Data Index: 8581268 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1674. Min Range: -7.1674
Max Act: 6.7299. Min Act: -0.1700
Data Index: 4940090 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1674. Min Range: -7.1674
Max Act: 6.7299. Min Act: -0.1700
Data Index: 7509178 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1674. Min Range: -7.1674
Max Act: 6.6674. Min Act: -0.1700
Data Index: 6224754 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1674. Min Range: -7.1674
Max Act: 6.6987. Min Act: -0.1700
Data Index: 771782 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1674. Min Range: -7.1674
Max Act: 6.6987. Min Act: -0.1700
Data Index: 6916811 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1674. Min Range: -7.1674
Max Act: 6.6987. Min Act: -0.1700
Data Index: 2501600 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1674. Min Range: -7.1674
Max Act: 6.6987. Min Act: -0.1700
Data Index: 6003321 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1674. Min Range: -7.1674
Max Act: 6.6674. Min Act: -0.1700
Data Index: 6598290 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1674. Min Range: -7.1674
Max Act: 6.6674. Min Act: -0.1700
Data Index: 6636717 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1674. Min Range: -7.1674
Max Act: 6.6674. Min Act: -0.1700
Data Index: 4319471 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1674. Min Range: -7.1674
Max Act: 6.6362. Min Act: -0.1700
Data Index: 1281819 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1674. Min Range: -7.1674
Max Act: 6.6674. Min Act: -0.1700
Data Index: 6761000 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1674. Min Range: -7.1674
Max Act: 6.6674. Min Act: -0.1700
Data Index: 2348916 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1674. Min Range: -7.1674
Max Act: 6.6674. Min Act: -0.1700
Data Index: 6557738 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1674. Min Range: -7.1674
Max Act: 6.6987. Min Act: -0.1700
Data Index: 2658258 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #19