Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 957 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7526. Min Range: -8.7526
Max Act: 8.7526. Min Act: -0.1700
Data Index: 1921315 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7526. Min Range: -8.7526
Max Act: 8.1276. Min Act: -0.1700
Data Index: 3276188 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7526. Min Range: -8.7526
Max Act: 8.0651. Min Act: -0.1700
Data Index: 2845354 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7526. Min Range: -8.7526
Max Act: 7.7526. Min Act: -0.1700
Data Index: 4775690 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7526. Min Range: -8.7526
Max Act: 7.6901. Min Act: -0.1700
Data Index: 1920827 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7526. Min Range: -8.7526
Max Act: 7.6276. Min Act: -0.1700
Data Index: 161562 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7526. Min Range: -8.7526
Max Act: 7.5963. Min Act: -0.1700
Data Index: 7250674 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7526. Min Range: -8.7526
Max Act: 7.5338. Min Act: -0.1700
Data Index: 998994 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7526. Min Range: -8.7526
Max Act: 7.5026. Min Act: -0.1700
Data Index: 7113162 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7526. Min Range: -8.7526
Max Act: 7.5026. Min Act: -0.1700
Data Index: 8481461 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7526. Min Range: -8.7526
Max Act: 7.5026. Min Act: -0.1700
Data Index: 964292 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7526. Min Range: -8.7526
Max Act: 7.4713. Min Act: -0.1700
Data Index: 2445056 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7526. Min Range: -8.7526
Max Act: 7.4088. Min Act: -0.1700
Data Index: 2294142 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7526. Min Range: -8.7526
Max Act: 7.4401. Min Act: -0.1700
Data Index: 3349404 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7526. Min Range: -8.7526
Max Act: 7.4401. Min Act: -0.1700
Data Index: 5019595 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7526. Min Range: -8.7526
Max Act: 7.4401. Min Act: -0.1700
Data Index: 2989927 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7526. Min Range: -8.7526
Max Act: 7.4088. Min Act: -0.1700
Data Index: 289233 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7526. Min Range: -8.7526
Max Act: 7.4088. Min Act: -0.1700
Data Index: 8274433 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7526. Min Range: -8.7526
Max Act: 7.4088. Min Act: -0.1700
Data Index: 7734445 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7526. Min Range: -8.7526
Max Act: 7.3776. Min Act: -0.1700
Data Index: 2089791 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #19