Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3857 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.1884. Min Range: -2.1884
Max Act: 2.1884. Min Act: -0.1700
Data Index: 8275638 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1884. Min Range: -2.1884
Max Act: 2.1050. Min Act: -0.1700
Data Index: 3368274 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1884. Min Range: -2.1884
Max Act: 2.1050. Min Act: -0.1700
Data Index: 6581514 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1884. Min Range: -2.1884
Max Act: 2.1217. Min Act: -0.1700
Data Index: 4930026 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1884. Min Range: -2.1884
Max Act: 2.0882. Min Act: -0.1700
Data Index: 7589285 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1884. Min Range: -2.1884
Max Act: 2.0715. Min Act: -0.1700
Data Index: 190600 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1884. Min Range: -2.1884
Max Act: 2.0715. Min Act: -0.1700
Data Index: 4936667 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1884. Min Range: -2.1884
Max Act: 2.0882. Min Act: -0.1700
Data Index: 4613273 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1884. Min Range: -2.1884
Max Act: 2.0547. Min Act: -0.1700
Data Index: 3267306 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1884. Min Range: -2.1884
Max Act: 2.0547. Min Act: -0.1700
Data Index: 7494069 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1884. Min Range: -2.1884
Max Act: 2.0715. Min Act: -0.1700
Data Index: 8146027 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1884. Min Range: -2.1884
Max Act: 2.0547. Min Act: -0.1700
Data Index: 8647203 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1884. Min Range: -2.1884
Max Act: 2.0378. Min Act: -0.1700
Data Index: 6903450 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1884. Min Range: -2.1884
Max Act: 2.0378. Min Act: -0.1700
Data Index: 8208729 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1884. Min Range: -2.1884
Max Act: 2.0378. Min Act: -0.1700
Data Index: 6428156 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1884. Min Range: -2.1884
Max Act: 2.0041. Min Act: -0.1700
Data Index: 4987342 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1884. Min Range: -2.1884
Max Act: 2.0210. Min Act: -0.1700
Data Index: 164292 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1884. Min Range: -2.1884
Max Act: 1.9872. Min Act: -0.1700
Data Index: 4443226 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1884. Min Range: -2.1884
Max Act: 2.0041. Min Act: -0.1700
Data Index: 4987343 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1884. Min Range: -2.1884
Max Act: 2.0041. Min Act: -0.1700
Data Index: 1084602 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #19