Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4731 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3901. Min Range: -7.3901
Max Act: 7.3901. Min Act: -0.1700
Data Index: 4061400 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3901. Min Range: -7.3901
Max Act: 7.3276. Min Act: -0.1700
Data Index: 94631 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3901. Min Range: -7.3901
Max Act: 7.2964. Min Act: -0.1700
Data Index: 1365768 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3901. Min Range: -7.3901
Max Act: 7.2026. Min Act: -0.1700
Data Index: 1212056 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3901. Min Range: -7.3901
Max Act: 7.1714. Min Act: -0.1700
Data Index: 8715792 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3901. Min Range: -7.3901
Max Act: 7.1714. Min Act: -0.1700
Data Index: 4429989 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3901. Min Range: -7.3901
Max Act: 7.1714. Min Act: -0.1700
Data Index: 714267 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3901. Min Range: -7.3901
Max Act: 7.0776. Min Act: -0.1700
Data Index: 3244003 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3901. Min Range: -7.3901
Max Act: 7.0464. Min Act: -0.1700
Data Index: 1333340 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3901. Min Range: -7.3901
Max Act: 7.0151. Min Act: -0.1700
Data Index: 6345911 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3901. Min Range: -7.3901
Max Act: 6.9839. Min Act: -0.1700
Data Index: 7433606 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3901. Min Range: -7.3901
Max Act: 6.9526. Min Act: -0.1700
Data Index: 3372774 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3901. Min Range: -7.3901
Max Act: 6.9214. Min Act: -0.1700
Data Index: 3714112 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3901. Min Range: -7.3901
Max Act: 6.8901. Min Act: -0.1700
Data Index: 2232858 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3901. Min Range: -7.3901
Max Act: 6.8901. Min Act: -0.1700
Data Index: 1622283 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3901. Min Range: -7.3901
Max Act: 6.8589. Min Act: -0.1700
Data Index: 5093840 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3901. Min Range: -7.3901
Max Act: 6.8276. Min Act: -0.1700
Data Index: 1352375 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3901. Min Range: -7.3901
Max Act: 6.8276. Min Act: -0.1700
Data Index: 1988716 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3901. Min Range: -7.3901
Max Act: 6.8276. Min Act: -0.1700
Data Index: 1977376 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3901. Min Range: -7.3901
Max Act: 6.7964. Min Act: -0.1700
Data Index: 6383015 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #19