Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4770 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4055. Min Range: -7.4055
Max Act: 7.4055. Min Act: -0.1700
Data Index: 4089070 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4055. Min Range: -7.4055
Max Act: 7.2493. Min Act: -0.1700
Data Index: 4093745 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4055. Min Range: -7.4055
Max Act: 7.2180. Min Act: -0.1700
Data Index: 8310734 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4055. Min Range: -7.4055
Max Act: 7.1555. Min Act: -0.1700
Data Index: 1071003 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4055. Min Range: -7.4055
Max Act: 7.1868. Min Act: -0.1700
Data Index: 3163600 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4055. Min Range: -7.4055
Max Act: 7.1243. Min Act: -0.1700
Data Index: 6085931 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4055. Min Range: -7.4055
Max Act: 7.0930. Min Act: -0.1700
Data Index: 8187205 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4055. Min Range: -7.4055
Max Act: 7.0930. Min Act: -0.1700
Data Index: 576437 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4055. Min Range: -7.4055
Max Act: 7.0618. Min Act: -0.1700
Data Index: 3513463 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4055. Min Range: -7.4055
Max Act: 7.0618. Min Act: -0.1700
Data Index: 7076356 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4055. Min Range: -7.4055
Max Act: 7.0618. Min Act: -0.1700
Data Index: 5294288 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4055. Min Range: -7.4055
Max Act: 7.0618. Min Act: -0.1700
Data Index: 1568202 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4055. Min Range: -7.4055
Max Act: 7.0618. Min Act: -0.1700
Data Index: 6995593 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4055. Min Range: -7.4055
Max Act: 6.9993. Min Act: -0.1700
Data Index: 3626082 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4055. Min Range: -7.4055
Max Act: 6.9993. Min Act: -0.1700
Data Index: 2759743 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4055. Min Range: -7.4055
Max Act: 6.9993. Min Act: -0.1700
Data Index: 5142830 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4055. Min Range: -7.4055
Max Act: 6.9680. Min Act: -0.1700
Data Index: 4247696 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4055. Min Range: -7.4055
Max Act: 6.9368. Min Act: -0.1700
Data Index: 6299312 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4055. Min Range: -7.4055
Max Act: 6.9680. Min Act: -0.1700
Data Index: 7391091 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4055. Min Range: -7.4055
Max Act: 6.9680. Min Act: -0.1700
Data Index: 3363972 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #19