Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1867 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7377. Min Range: -7.7377
Max Act: 7.7377. Min Act: -0.1700
Data Index: 678570 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7377. Min Range: -7.7377
Max Act: 7.6127. Min Act: -0.1700
Data Index: 3857714 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7377. Min Range: -7.7377
Max Act: 7.6752. Min Act: -0.1700
Data Index: 3335053 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7377. Min Range: -7.7377
Max Act: 7.4564. Min Act: -0.1700
Data Index: 8350125 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7377. Min Range: -7.7377
Max Act: 7.3939. Min Act: -0.1700
Data Index: 6483441 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7377. Min Range: -7.7377
Max Act: 7.3627. Min Act: -0.1700
Data Index: 6310601 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7377. Min Range: -7.7377
Max Act: 7.3002. Min Act: -0.1700
Data Index: 946280 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7377. Min Range: -7.7377
Max Act: 7.3314. Min Act: -0.1700
Data Index: 3268636 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7377. Min Range: -7.7377
Max Act: 7.3002. Min Act: -0.1700
Data Index: 2273943 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7377. Min Range: -7.7377
Max Act: 7.2689. Min Act: -0.1700
Data Index: 2462374 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7377. Min Range: -7.7377
Max Act: 7.2377. Min Act: -0.1700
Data Index: 2426577 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7377. Min Range: -7.7377
Max Act: 7.2377. Min Act: -0.1700
Data Index: 6372656 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7377. Min Range: -7.7377
Max Act: 7.1752. Min Act: -0.1700
Data Index: 2537225 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7377. Min Range: -7.7377
Max Act: 7.1752. Min Act: -0.1700
Data Index: 783105 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7377. Min Range: -7.7377
Max Act: 7.1752. Min Act: -0.1700
Data Index: 6896826 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7377. Min Range: -7.7377
Max Act: 7.1752. Min Act: -0.1700
Data Index: 1722758 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7377. Min Range: -7.7377
Max Act: 7.1752. Min Act: -0.1700
Data Index: 5610467 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7377. Min Range: -7.7377
Max Act: 7.1439. Min Act: -0.1700
Data Index: 5201638 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7377. Min Range: -7.7377
Max Act: 7.0814. Min Act: -0.1700
Data Index: 4028182 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7377. Min Range: -7.7377
Max Act: 7.0814. Min Act: -0.1700
Data Index: 625336 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #19