Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4265 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6250. Min Range: -5.6250
Max Act: 5.6250. Min Act: -0.1700
Data Index: 5253922 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6250. Min Range: -5.6250
Max Act: 5.4375. Min Act: -0.1700
Data Index: 1701422 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6250. Min Range: -5.6250
Max Act: 5.4062. Min Act: -0.1700
Data Index: 1117811 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6250. Min Range: -5.6250
Max Act: 5.4062. Min Act: -0.1700
Data Index: 3617261 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6250. Min Range: -5.6250
Max Act: 5.4062. Min Act: -0.1700
Data Index: 1214061 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6250. Min Range: -5.6250
Max Act: 5.3750. Min Act: -0.1700
Data Index: 72233 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6250. Min Range: -5.6250
Max Act: 5.3437. Min Act: -0.1700
Data Index: 423050 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6250. Min Range: -5.6250
Max Act: 5.3125. Min Act: -0.1700
Data Index: 1513828 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6250. Min Range: -5.6250
Max Act: 5.2812. Min Act: -0.1700
Data Index: 5253923 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6250. Min Range: -5.6250
Max Act: 5.2812. Min Act: -0.1700
Data Index: 8711976 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6250. Min Range: -5.6250
Max Act: 5.2812. Min Act: -0.1700
Data Index: 2119041 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6250. Min Range: -5.6250
Max Act: 5.2500. Min Act: -0.1700
Data Index: 5599039 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6250. Min Range: -5.6250
Max Act: 5.2500. Min Act: -0.1700
Data Index: 5618959 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6250. Min Range: -5.6250
Max Act: 5.2187. Min Act: -0.1700
Data Index: 3604244 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6250. Min Range: -5.6250
Max Act: 5.2187. Min Act: -0.1700
Data Index: 8399169 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6250. Min Range: -5.6250
Max Act: 5.2500. Min Act: -0.1700
Data Index: 7529301 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6250. Min Range: -5.6250
Max Act: 5.2187. Min Act: -0.1700
Data Index: 44799 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6250. Min Range: -5.6250
Max Act: 5.2500. Min Act: -0.1700
Data Index: 3407772 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6250. Min Range: -5.6250
Max Act: 5.1875. Min Act: -0.1700
Data Index: 8322501 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6250. Min Range: -5.6250
Max Act: 5.1875. Min Act: -0.1700
Data Index: 5177484 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #19