Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2227 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9142. Min Range: -2.9142
Max Act: 2.9142. Min Act: -0.1700
Data Index: 2810803 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9142. Min Range: -2.9142
Max Act: 2.8348. Min Act: -0.1700
Data Index: 3088630 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9142. Min Range: -2.9142
Max Act: 2.8348. Min Act: -0.1700
Data Index: 2204038 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9142. Min Range: -2.9142
Max Act: 2.8189. Min Act: -0.1700
Data Index: 3497542 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9142. Min Range: -2.9142
Max Act: 2.8030. Min Act: -0.1700
Data Index: 3404919 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9142. Min Range: -2.9142
Max Act: 2.8030. Min Act: -0.1700
Data Index: 1961947 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9142. Min Range: -2.9142
Max Act: 2.7870. Min Act: -0.1700
Data Index: 7457607 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9142. Min Range: -2.9142
Max Act: 2.7551. Min Act: -0.1700
Data Index: 3517177 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9142. Min Range: -2.9142
Max Act: 2.7711. Min Act: -0.1700
Data Index: 226598 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9142. Min Range: -2.9142
Max Act: 2.7711. Min Act: -0.1700
Data Index: 2122621 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9142. Min Range: -2.9142
Max Act: 2.7551. Min Act: -0.1700
Data Index: 6087566 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9142. Min Range: -2.9142
Max Act: 2.7232. Min Act: -0.1700
Data Index: 6497555 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9142. Min Range: -2.9142
Max Act: 2.7232. Min Act: -0.1700
Data Index: 4737496 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9142. Min Range: -2.9142
Max Act: 2.7072. Min Act: -0.1700
Data Index: 63679 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9142. Min Range: -2.9142
Max Act: 2.7232. Min Act: -0.1700
Data Index: 7724782 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9142. Min Range: -2.9142
Max Act: 2.7232. Min Act: -0.1700
Data Index: 6187999 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9142. Min Range: -2.9142
Max Act: 2.7232. Min Act: -0.1700
Data Index: 3483523 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9142. Min Range: -2.9142
Max Act: 2.7232. Min Act: -0.1700
Data Index: 7648487 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9142. Min Range: -2.9142
Max Act: 2.7072. Min Act: -0.1700
Data Index: 1882656 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9142. Min Range: -2.9142
Max Act: 2.7072. Min Act: -0.1700
Data Index: 702197 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #19