Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5133 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6656. Min Range: -5.6656
Max Act: 5.6656. Min Act: -0.1700
Data Index: 8286688 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6656. Min Range: -5.6656
Max Act: 5.3844. Min Act: -0.1700
Data Index: 2527978 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6656. Min Range: -5.6656
Max Act: 5.3531. Min Act: -0.1700
Data Index: 774074 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6656. Min Range: -5.6656
Max Act: 5.2906. Min Act: -0.1700
Data Index: 1676826 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6656. Min Range: -5.6656
Max Act: 5.2594. Min Act: -0.1700
Data Index: 4263974 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6656. Min Range: -5.6656
Max Act: 5.1656. Min Act: -0.1700
Data Index: 5396879 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6656. Min Range: -5.6656
Max Act: 5.1344. Min Act: -0.1700
Data Index: 569471 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6656. Min Range: -5.6656
Max Act: 5.1344. Min Act: -0.1700
Data Index: 6172577 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6656. Min Range: -5.6656
Max Act: 5.1344. Min Act: -0.1700
Data Index: 6551767 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6656. Min Range: -5.6656
Max Act: 5.1344. Min Act: -0.1700
Data Index: 3092316 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6656. Min Range: -5.6656
Max Act: 5.0719. Min Act: -0.1700
Data Index: 8242178 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6656. Min Range: -5.6656
Max Act: 5.1031. Min Act: -0.1700
Data Index: 1583952 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6656. Min Range: -5.6656
Max Act: 5.0719. Min Act: -0.1700
Data Index: 7447608 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6656. Min Range: -5.6656
Max Act: 5.0719. Min Act: -0.1700
Data Index: 4757174 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6656. Min Range: -5.6656
Max Act: 5.0719. Min Act: -0.1700
Data Index: 194802 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6656. Min Range: -5.6656
Max Act: 5.0406. Min Act: -0.1700
Data Index: 5815530 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6656. Min Range: -5.6656
Max Act: 5.0406. Min Act: -0.1700
Data Index: 7243519 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6656. Min Range: -5.6656
Max Act: 5.0406. Min Act: -0.1700
Data Index: 6989518 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6656. Min Range: -5.6656
Max Act: 5.0406. Min Act: -0.1700
Data Index: 3639685 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6656. Min Range: -5.6656
Max Act: 5.0719. Min Act: -0.1700
Data Index: 5044318 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #19