Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3453 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7075. Min Range: -4.7075
Max Act: 4.7075. Min Act: -0.1700
Data Index: 2266191 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7075. Min Range: -4.7075
Max Act: 4.5200. Min Act: -0.1700
Data Index: 3470706 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7075. Min Range: -4.7075
Max Act: 4.4575. Min Act: -0.1700
Data Index: 1348637 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7075. Min Range: -4.7075
Max Act: 4.4575. Min Act: -0.1700
Data Index: 7119840 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7075. Min Range: -4.7075
Max Act: 4.3950. Min Act: -0.1700
Data Index: 8264721 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7075. Min Range: -4.7075
Max Act: 4.3950. Min Act: -0.1700
Data Index: 6558745 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7075. Min Range: -4.7075
Max Act: 4.3638. Min Act: -0.1700
Data Index: 1997298 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7075. Min Range: -4.7075
Max Act: 4.3638. Min Act: -0.1700
Data Index: 2897308 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7075. Min Range: -4.7075
Max Act: 4.3325. Min Act: -0.1700
Data Index: 7164410 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7075. Min Range: -4.7075
Max Act: 4.3013. Min Act: -0.1700
Data Index: 7553472 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7075. Min Range: -4.7075
Max Act: 4.3013. Min Act: -0.1700
Data Index: 4913275 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7075. Min Range: -4.7075
Max Act: 4.3013. Min Act: -0.1700
Data Index: 3196774 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7075. Min Range: -4.7075
Max Act: 4.3013. Min Act: -0.1700
Data Index: 1875439 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7075. Min Range: -4.7075
Max Act: 4.2387. Min Act: -0.1700
Data Index: 1995113 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7075. Min Range: -4.7075
Max Act: 4.2075. Min Act: -0.1700
Data Index: 6230977 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7075. Min Range: -4.7075
Max Act: 4.2387. Min Act: -0.1700
Data Index: 205338 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7075. Min Range: -4.7075
Max Act: 4.2387. Min Act: -0.1700
Data Index: 6747951 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7075. Min Range: -4.7075
Max Act: 4.2075. Min Act: -0.1700
Data Index: 8104472 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7075. Min Range: -4.7075
Max Act: 4.2075. Min Act: -0.1700
Data Index: 5572654 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7075. Min Range: -4.7075
Max Act: 4.2075. Min Act: -0.1700
Data Index: 6138558 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #19