Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4475 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3250. Min Range: -7.3250
Max Act: 7.3250. Min Act: -0.1700
Data Index: 8077992 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3250. Min Range: -7.3250
Max Act: 7.2937. Min Act: -0.1700
Data Index: 7719024 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3250. Min Range: -7.3250
Max Act: 7.2312. Min Act: -0.1700
Data Index: 4298413 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3250. Min Range: -7.3250
Max Act: 7.2625. Min Act: -0.1700
Data Index: 6011324 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3250. Min Range: -7.3250
Max Act: 7.2625. Min Act: -0.1700
Data Index: 6264397 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3250. Min Range: -7.3250
Max Act: 7.2312. Min Act: -0.1700
Data Index: 4635495 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3250. Min Range: -7.3250
Max Act: 7.2312. Min Act: -0.1700
Data Index: 6294208 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3250. Min Range: -7.3250
Max Act: 7.2000. Min Act: -0.1700
Data Index: 193321 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3250. Min Range: -7.3250
Max Act: 7.2000. Min Act: -0.1700
Data Index: 5770406 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3250. Min Range: -7.3250
Max Act: 7.2000. Min Act: -0.1700
Data Index: 5502124 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3250. Min Range: -7.3250
Max Act: 7.2000. Min Act: -0.1700
Data Index: 2763680 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3250. Min Range: -7.3250
Max Act: 7.2000. Min Act: -0.1700
Data Index: 717663 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3250. Min Range: -7.3250
Max Act: 7.2000. Min Act: -0.1700
Data Index: 7466555 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3250. Min Range: -7.3250
Max Act: 7.1687. Min Act: -0.1700
Data Index: 4728472 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3250. Min Range: -7.3250
Max Act: 7.1375. Min Act: -0.1700
Data Index: 3765306 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3250. Min Range: -7.3250
Max Act: 7.1687. Min Act: -0.1700
Data Index: 443423 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3250. Min Range: -7.3250
Max Act: 7.1687. Min Act: -0.1700
Data Index: 4454563 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3250. Min Range: -7.3250
Max Act: 7.1687. Min Act: -0.1700
Data Index: 7410098 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3250. Min Range: -7.3250
Max Act: 7.1375. Min Act: -0.1700
Data Index: 7028427 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3250. Min Range: -7.3250
Max Act: 7.1375. Min Act: -0.1700
Data Index: 1740670 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #19