Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 625 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6740. Min Range: -4.6740
Max Act: 4.6740. Min Act: -0.1700
Data Index: 5747329 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6740. Min Range: -4.6740
Max Act: 4.6740. Min Act: -0.1700
Data Index: 718124 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6740. Min Range: -4.6740
Max Act: 4.6115. Min Act: -0.1700
Data Index: 7424593 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6740. Min Range: -4.6740
Max Act: 4.6115. Min Act: -0.1700
Data Index: 1615875 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6740. Min Range: -4.6740
Max Act: 4.5490. Min Act: -0.1700
Data Index: 1406379 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6740. Min Range: -4.6740
Max Act: 4.5490. Min Act: -0.1700
Data Index: 4007095 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6740. Min Range: -4.6740
Max Act: 4.5177. Min Act: -0.1700
Data Index: 7190300 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6740. Min Range: -4.6740
Max Act: 4.4552. Min Act: -0.1700
Data Index: 5912411 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6740. Min Range: -4.6740
Max Act: 4.4240. Min Act: -0.1700
Data Index: 2991724 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6740. Min Range: -4.6740
Max Act: 4.4240. Min Act: -0.1700
Data Index: 3104075 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6740. Min Range: -4.6740
Max Act: 4.4240. Min Act: -0.1700
Data Index: 32426 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6740. Min Range: -4.6740
Max Act: 4.4552. Min Act: -0.1700
Data Index: 1507743 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6740. Min Range: -4.6740
Max Act: 4.4240. Min Act: -0.1700
Data Index: 1191882 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6740. Min Range: -4.6740
Max Act: 4.4240. Min Act: -0.1700
Data Index: 5383222 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6740. Min Range: -4.6740
Max Act: 4.3927. Min Act: -0.1700
Data Index: 5638644 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6740. Min Range: -4.6740
Max Act: 4.3927. Min Act: -0.1700
Data Index: 2039232 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6740. Min Range: -4.6740
Max Act: 4.3927. Min Act: -0.1700
Data Index: 2617981 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6740. Min Range: -4.6740
Max Act: 4.3927. Min Act: -0.1700
Data Index: 4733678 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6740. Min Range: -4.6740
Max Act: 4.3615. Min Act: -0.1700
Data Index: 1067637 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6740. Min Range: -4.6740
Max Act: 4.3615. Min Act: -0.1700
Data Index: 3122026 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #19