Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3269 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5601. Min Range: -3.5601
Max Act: 3.5601. Min Act: -0.1700
Data Index: 1537035 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5601. Min Range: -3.5601
Max Act: 3.5132. Min Act: -0.1700
Data Index: 4033351 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5601. Min Range: -3.5601
Max Act: 3.3408. Min Act: -0.1700
Data Index: 8286576 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5601. Min Range: -3.5601
Max Act: 3.3094. Min Act: -0.1700
Data Index: 1523554 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5601. Min Range: -3.5601
Max Act: 3.2780. Min Act: -0.1700
Data Index: 7842641 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5601. Min Range: -3.5601
Max Act: 3.2937. Min Act: -0.1700
Data Index: 2543951 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5601. Min Range: -3.5601
Max Act: 3.2937. Min Act: -0.1700
Data Index: 8385584 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5601. Min Range: -3.5601
Max Act: 3.2780. Min Act: -0.1700
Data Index: 8597349 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5601. Min Range: -3.5601
Max Act: 3.2780. Min Act: -0.1700
Data Index: 7619026 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5601. Min Range: -3.5601
Max Act: 3.2308. Min Act: -0.1700
Data Index: 5726255 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5601. Min Range: -3.5601
Max Act: 3.2308. Min Act: -0.1700
Data Index: 2197197 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5601. Min Range: -3.5601
Max Act: 3.2151. Min Act: -0.1700
Data Index: 76411 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5601. Min Range: -3.5601
Max Act: 3.1994. Min Act: -0.1700
Data Index: 81484 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5601. Min Range: -3.5601
Max Act: 3.1679. Min Act: -0.1700
Data Index: 2188821 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5601. Min Range: -3.5601
Max Act: 3.1679. Min Act: -0.1700
Data Index: 3875223 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5601. Min Range: -3.5601
Max Act: 3.1522. Min Act: -0.1700
Data Index: 5739510 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5601. Min Range: -3.5601
Max Act: 3.1364. Min Act: -0.1700
Data Index: 1624118 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5601. Min Range: -3.5601
Max Act: 3.1207. Min Act: -0.1700
Data Index: 764478 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5601. Min Range: -3.5601
Max Act: 3.1364. Min Act: -0.1700
Data Index: 3678763 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5601. Min Range: -3.5601
Max Act: 3.1364. Min Act: -0.1700
Data Index: 8360309 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #19