Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5251 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4620. Min Range: -7.4620
Max Act: 7.4620. Min Act: -0.1700
Data Index: 2866557 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4620. Min Range: -7.4620
Max Act: 7.4308. Min Act: -0.1700
Data Index: 8005717 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4620. Min Range: -7.4620
Max Act: 7.3058. Min Act: -0.1700
Data Index: 6664898 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4620. Min Range: -7.4620
Max Act: 7.3370. Min Act: -0.1700
Data Index: 6306868 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4620. Min Range: -7.4620
Max Act: 7.3370. Min Act: -0.1700
Data Index: 4995392 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4620. Min Range: -7.4620
Max Act: 7.2120. Min Act: -0.1700
Data Index: 7121143 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4620. Min Range: -7.4620
Max Act: 7.2433. Min Act: -0.1700
Data Index: 2713373 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4620. Min Range: -7.4620
Max Act: 7.2433. Min Act: -0.1700
Data Index: 2885286 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4620. Min Range: -7.4620
Max Act: 7.1495. Min Act: -0.1700
Data Index: 3262747 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4620. Min Range: -7.4620
Max Act: 7.0870. Min Act: -0.1700
Data Index: 2090151 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4620. Min Range: -7.4620
Max Act: 7.0870. Min Act: -0.1700
Data Index: 782101 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4620. Min Range: -7.4620
Max Act: 7.0870. Min Act: -0.1700
Data Index: 6060439 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4620. Min Range: -7.4620
Max Act: 7.0558. Min Act: -0.1700
Data Index: 5524703 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4620. Min Range: -7.4620
Max Act: 7.0245. Min Act: -0.1700
Data Index: 2219899 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4620. Min Range: -7.4620
Max Act: 7.0245. Min Act: -0.1700
Data Index: 7201820 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4620. Min Range: -7.4620
Max Act: 7.0245. Min Act: -0.1700
Data Index: 5732362 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4620. Min Range: -7.4620
Max Act: 7.0245. Min Act: -0.1700
Data Index: 7456883 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4620. Min Range: -7.4620
Max Act: 6.9620. Min Act: -0.1700
Data Index: 5083259 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4620. Min Range: -7.4620
Max Act: 6.9933. Min Act: -0.1700
Data Index: 3514044 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4620. Min Range: -7.4620
Max Act: 6.9933. Min Act: -0.1700
Data Index: 6814198 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #19