Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2618 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3794. Min Range: -7.3794
Max Act: 7.3794. Min Act: -0.1700
Data Index: 4946256 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3794. Min Range: -7.3794
Max Act: 7.0669. Min Act: -0.1700
Data Index: 584796 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3794. Min Range: -7.3794
Max Act: 6.9732. Min Act: -0.1700
Data Index: 2755665 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3794. Min Range: -7.3794
Max Act: 6.9107. Min Act: -0.1700
Data Index: 8321628 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3794. Min Range: -7.3794
Max Act: 6.8794. Min Act: -0.1700
Data Index: 8708453 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3794. Min Range: -7.3794
Max Act: 6.9107. Min Act: -0.1700
Data Index: 6353643 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3794. Min Range: -7.3794
Max Act: 6.9107. Min Act: -0.1700
Data Index: 830717 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3794. Min Range: -7.3794
Max Act: 6.8794. Min Act: -0.1700
Data Index: 3614639 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3794. Min Range: -7.3794
Max Act: 6.8482. Min Act: -0.1700
Data Index: 5864583 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3794. Min Range: -7.3794
Max Act: 6.8482. Min Act: -0.1700
Data Index: 8744270 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3794. Min Range: -7.3794
Max Act: 6.8169. Min Act: -0.1700
Data Index: 4868763 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3794. Min Range: -7.3794
Max Act: 6.8169. Min Act: -0.1700
Data Index: 8487679 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3794. Min Range: -7.3794
Max Act: 6.7857. Min Act: -0.1700
Data Index: 7602275 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3794. Min Range: -7.3794
Max Act: 6.8169. Min Act: -0.1700
Data Index: 2628564 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3794. Min Range: -7.3794
Max Act: 6.7544. Min Act: -0.1700
Data Index: 171375 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3794. Min Range: -7.3794
Max Act: 6.7857. Min Act: -0.1700
Data Index: 1867512 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3794. Min Range: -7.3794
Max Act: 6.7857. Min Act: -0.1700
Data Index: 4952163 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3794. Min Range: -7.3794
Max Act: 6.7857. Min Act: -0.1700
Data Index: 5472200 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3794. Min Range: -7.3794
Max Act: 6.7544. Min Act: -0.1700
Data Index: 6880220 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3794. Min Range: -7.3794
Max Act: 6.7544. Min Act: -0.1700
Data Index: 3599833 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #19