Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3484 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7093. Min Range: -6.7093
Max Act: 6.7093. Min Act: -0.1700
Data Index: 4958029 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7093. Min Range: -6.7093
Max Act: 6.4593. Min Act: -0.1700
Data Index: 6168099 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7093. Min Range: -6.7093
Max Act: 6.4593. Min Act: -0.1700
Data Index: 5181663 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7093. Min Range: -6.7093
Max Act: 6.4281. Min Act: -0.1700
Data Index: 5448134 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7093. Min Range: -6.7093
Max Act: 6.4281. Min Act: -0.1700
Data Index: 59187 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7093. Min Range: -6.7093
Max Act: 6.3656. Min Act: -0.1700
Data Index: 1645615 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7093. Min Range: -6.7093
Max Act: 6.3656. Min Act: -0.1700
Data Index: 7648411 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7093. Min Range: -6.7093
Max Act: 6.3656. Min Act: -0.1700
Data Index: 6505034 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7093. Min Range: -6.7093
Max Act: 6.3343. Min Act: -0.1700
Data Index: 4622520 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7093. Min Range: -6.7093
Max Act: 6.3656. Min Act: -0.1700
Data Index: 6526676 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7093. Min Range: -6.7093
Max Act: 6.3343. Min Act: -0.1700
Data Index: 6452580 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7093. Min Range: -6.7093
Max Act: 6.3343. Min Act: -0.1700
Data Index: 1208364 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7093. Min Range: -6.7093
Max Act: 6.3343. Min Act: -0.1700
Data Index: 7787227 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7093. Min Range: -6.7093
Max Act: 6.3031. Min Act: -0.1700
Data Index: 1008237 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7093. Min Range: -6.7093
Max Act: 6.3031. Min Act: -0.1700
Data Index: 3376555 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7093. Min Range: -6.7093
Max Act: 6.3031. Min Act: -0.1700
Data Index: 8533794 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7093. Min Range: -6.7093
Max Act: 6.2406. Min Act: -0.1700
Data Index: 2064793 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7093. Min Range: -6.7093
Max Act: 6.2718. Min Act: -0.1700
Data Index: 519276 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7093. Min Range: -6.7093
Max Act: 6.2718. Min Act: -0.1700
Data Index: 8466339 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7093. Min Range: -6.7093
Max Act: 6.2406. Min Act: -0.1700
Data Index: 6000678 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #19