Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5906 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5630. Min Range: -3.5630
Max Act: 3.5630. Min Act: -0.1700
Data Index: 2942665 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5630. Min Range: -3.5630
Max Act: 3.5630. Min Act: -0.1700
Data Index: 7803184 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5630. Min Range: -3.5630
Max Act: 3.4847. Min Act: -0.1700
Data Index: 4190802 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5630. Min Range: -3.5630
Max Act: 3.4690. Min Act: -0.1700
Data Index: 8296028 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5630. Min Range: -3.5630
Max Act: 3.4690. Min Act: -0.1700
Data Index: 5912731 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5630. Min Range: -3.5630
Max Act: 3.4533. Min Act: -0.1700
Data Index: 8656373 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5630. Min Range: -3.5630
Max Act: 3.4533. Min Act: -0.1700
Data Index: 5234570 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5630. Min Range: -3.5630
Max Act: 3.4533. Min Act: -0.1700
Data Index: 4503665 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5630. Min Range: -3.5630
Max Act: 3.4377. Min Act: -0.1700
Data Index: 5095455 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5630. Min Range: -3.5630
Max Act: 3.4220. Min Act: -0.1700
Data Index: 5863029 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5630. Min Range: -3.5630
Max Act: 3.4220. Min Act: -0.1700
Data Index: 7589825 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5630. Min Range: -3.5630
Max Act: 3.4063. Min Act: -0.1700
Data Index: 8164795 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5630. Min Range: -3.5630
Max Act: 3.3906. Min Act: -0.1700
Data Index: 1616892 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5630. Min Range: -3.5630
Max Act: 3.3906. Min Act: -0.1700
Data Index: 1362385 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5630. Min Range: -3.5630
Max Act: 3.3749. Min Act: -0.1700
Data Index: 3647035 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5630. Min Range: -3.5630
Max Act: 3.3906. Min Act: -0.1700
Data Index: 3444554 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5630. Min Range: -3.5630
Max Act: 3.3906. Min Act: -0.1700
Data Index: 1159775 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5630. Min Range: -3.5630
Max Act: 3.3749. Min Act: -0.1700
Data Index: 577949 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5630. Min Range: -3.5630
Max Act: 3.3593. Min Act: -0.1700
Data Index: 4182273 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5630. Min Range: -3.5630
Max Act: 3.3593. Min Act: -0.1700
Data Index: 7423061 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #19