Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1796 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0815. Min Range: -7.0815
Max Act: 7.0815. Min Act: -0.1700
Data Index: 4300966 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0815. Min Range: -7.0815
Max Act: 6.8940. Min Act: -0.1700
Data Index: 1311731 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0815. Min Range: -7.0815
Max Act: 6.7690. Min Act: -0.1700
Data Index: 624847 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0815. Min Range: -7.0815
Max Act: 6.7065. Min Act: -0.1700
Data Index: 3228575 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0815. Min Range: -7.0815
Max Act: 6.6752. Min Act: -0.1700
Data Index: 1715267 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0815. Min Range: -7.0815
Max Act: 6.5815. Min Act: -0.1700
Data Index: 4886447 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0815. Min Range: -7.0815
Max Act: 6.5815. Min Act: -0.1700
Data Index: 8734404 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0815. Min Range: -7.0815
Max Act: 6.4565. Min Act: -0.1700
Data Index: 3180116 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0815. Min Range: -7.0815
Max Act: 6.4565. Min Act: -0.1700
Data Index: 4409270 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0815. Min Range: -7.0815
Max Act: 6.4252. Min Act: -0.1700
Data Index: 1195268 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0815. Min Range: -7.0815
Max Act: 6.4252. Min Act: -0.1700
Data Index: 6149104 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0815. Min Range: -7.0815
Max Act: 6.4252. Min Act: -0.1700
Data Index: 3180118 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0815. Min Range: -7.0815
Max Act: 6.3940. Min Act: -0.1700
Data Index: 2018023 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0815. Min Range: -7.0815
Max Act: 6.3940. Min Act: -0.1700
Data Index: 1863830 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0815. Min Range: -7.0815
Max Act: 6.3940. Min Act: -0.1700
Data Index: 6481096 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0815. Min Range: -7.0815
Max Act: 6.3627. Min Act: -0.1700
Data Index: 4086520 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0815. Min Range: -7.0815
Max Act: 6.3315. Min Act: -0.1700
Data Index: 8007146 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0815. Min Range: -7.0815
Max Act: 6.3627. Min Act: -0.1700
Data Index: 8316988 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0815. Min Range: -7.0815
Max Act: 6.3315. Min Act: -0.1700
Data Index: 3971813 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0815. Min Range: -7.0815
Max Act: 6.3002. Min Act: -0.1700
Data Index: 6735517 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #19