Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3449 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9259. Min Range: -7.9259
Max Act: 7.9259. Min Act: -0.1700
Data Index: 7541826 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9259. Min Range: -7.9259
Max Act: 7.8009. Min Act: -0.1700
Data Index: 2810056 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9259. Min Range: -7.9259
Max Act: 7.8009. Min Act: -0.1700
Data Index: 7095157 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9259. Min Range: -7.9259
Max Act: 7.7384. Min Act: -0.1700
Data Index: 5412825 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9259. Min Range: -7.9259
Max Act: 7.7384. Min Act: -0.1700
Data Index: 5435874 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9259. Min Range: -7.9259
Max Act: 7.7071. Min Act: -0.1700
Data Index: 3021817 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9259. Min Range: -7.9259
Max Act: 7.7071. Min Act: -0.1700
Data Index: 1158559 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9259. Min Range: -7.9259
Max Act: 7.6759. Min Act: -0.1700
Data Index: 5670841 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9259. Min Range: -7.9259
Max Act: 7.6134. Min Act: -0.1700
Data Index: 7541823 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9259. Min Range: -7.9259
Max Act: 7.6446. Min Act: -0.1700
Data Index: 2968740 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9259. Min Range: -7.9259
Max Act: 7.6134. Min Act: -0.1700
Data Index: 2810051 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9259. Min Range: -7.9259
Max Act: 7.5821. Min Act: -0.1700
Data Index: 7541824 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9259. Min Range: -7.9259
Max Act: 7.5509. Min Act: -0.1700
Data Index: 514251 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9259. Min Range: -7.9259
Max Act: 7.5509. Min Act: -0.1700
Data Index: 1348682 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9259. Min Range: -7.9259
Max Act: 7.5196. Min Act: -0.1700
Data Index: 7337982 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9259. Min Range: -7.9259
Max Act: 7.4884. Min Act: -0.1700
Data Index: 3025489 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9259. Min Range: -7.9259
Max Act: 7.4884. Min Act: -0.1700
Data Index: 2810057 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9259. Min Range: -7.9259
Max Act: 7.4884. Min Act: -0.1700
Data Index: 4045991 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9259. Min Range: -7.9259
Max Act: 7.4571. Min Act: -0.1700
Data Index: 3074437 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9259. Min Range: -7.9259
Max Act: 7.4259. Min Act: -0.1700
Data Index: 3636142 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #19