Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3031 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7759. Min Range: -4.7759
Max Act: 4.7759. Min Act: -0.1700
Data Index: 7269157 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7759. Min Range: -4.7759
Max Act: 4.7134. Min Act: -0.1700
Data Index: 809120 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7759. Min Range: -4.7759
Max Act: 4.7134. Min Act: -0.1700
Data Index: 7267735 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7759. Min Range: -4.7759
Max Act: 4.6821. Min Act: -0.1700
Data Index: 2894148 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7759. Min Range: -4.7759
Max Act: 4.6509. Min Act: -0.1700
Data Index: 8212637 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7759. Min Range: -4.7759
Max Act: 4.6509. Min Act: -0.1700
Data Index: 6558232 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7759. Min Range: -4.7759
Max Act: 4.6509. Min Act: -0.1700
Data Index: 8627589 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7759. Min Range: -4.7759
Max Act: 4.6196. Min Act: -0.1700
Data Index: 1106374 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7759. Min Range: -4.7759
Max Act: 4.5884. Min Act: -0.1700
Data Index: 5554372 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7759. Min Range: -4.7759
Max Act: 4.5571. Min Act: -0.1700
Data Index: 2931107 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7759. Min Range: -4.7759
Max Act: 4.5884. Min Act: -0.1700
Data Index: 605350 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7759. Min Range: -4.7759
Max Act: 4.5259. Min Act: -0.1700
Data Index: 1874715 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7759. Min Range: -4.7759
Max Act: 4.5259. Min Act: -0.1700
Data Index: 1497953 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7759. Min Range: -4.7759
Max Act: 4.5259. Min Act: -0.1700
Data Index: 5567466 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7759. Min Range: -4.7759
Max Act: 4.5259. Min Act: -0.1700
Data Index: 5381140 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7759. Min Range: -4.7759
Max Act: 4.4634. Min Act: -0.1700
Data Index: 8229599 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7759. Min Range: -4.7759
Max Act: 4.4634. Min Act: -0.1700
Data Index: 4884135 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7759. Min Range: -4.7759
Max Act: 4.4634. Min Act: -0.1700
Data Index: 3336104 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7759. Min Range: -4.7759
Max Act: 4.4321. Min Act: -0.1700
Data Index: 840082 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7759. Min Range: -4.7759
Max Act: 4.4321. Min Act: -0.1700
Data Index: 5520113 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #19