Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5713 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4929. Min Range: -6.4929
Max Act: 6.4617. Min Act: -0.1700
Data Index: 8472591 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4929. Min Range: -6.4929
Max Act: 6.4617. Min Act: -0.1700
Data Index: 2724445 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4929. Min Range: -6.4929
Max Act: 6.4617. Min Act: -0.1700
Data Index: 5537984 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4929. Min Range: -6.4929
Max Act: 6.4929. Min Act: -0.1700
Data Index: 3781181 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4929. Min Range: -6.4929
Max Act: 6.3992. Min Act: -0.1700
Data Index: 3723022 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4929. Min Range: -6.4929
Max Act: 6.3679. Min Act: -0.1700
Data Index: 8632679 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4929. Min Range: -6.4929
Max Act: 6.3679. Min Act: -0.1700
Data Index: 4866434 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4929. Min Range: -6.4929
Max Act: 6.3054. Min Act: -0.1700
Data Index: 1010422 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4929. Min Range: -6.4929
Max Act: 6.2742. Min Act: -0.1700
Data Index: 3938131 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4929. Min Range: -6.4929
Max Act: 6.3054. Min Act: -0.1700
Data Index: 4374442 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4929. Min Range: -6.4929
Max Act: 6.2429. Min Act: -0.1700
Data Index: 8498129 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4929. Min Range: -6.4929
Max Act: 6.2429. Min Act: -0.1700
Data Index: 2486193 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4929. Min Range: -6.4929
Max Act: 6.2429. Min Act: -0.1700
Data Index: 4757489 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4929. Min Range: -6.4929
Max Act: 6.2429. Min Act: -0.1700
Data Index: 8351362 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4929. Min Range: -6.4929
Max Act: 6.2117. Min Act: -0.1700
Data Index: 4587737 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4929. Min Range: -6.4929
Max Act: 6.2117. Min Act: -0.1700
Data Index: 5171519 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4929. Min Range: -6.4929
Max Act: 6.2117. Min Act: -0.1700
Data Index: 2238002 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4929. Min Range: -6.4929
Max Act: 6.1804. Min Act: -0.1700
Data Index: 2188873 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4929. Min Range: -6.4929
Max Act: 6.1804. Min Act: -0.1700
Data Index: 3316331 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4929. Min Range: -6.4929
Max Act: 6.2117. Min Act: -0.1700
Data Index: 5742895 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #19