Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1764 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0897. Min Range: -8.0897
Max Act: 8.0897. Min Act: -0.1700
Data Index: 7240529 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0897. Min Range: -8.0897
Max Act: 8.0272. Min Act: -0.1700
Data Index: 3587274 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0897. Min Range: -8.0897
Max Act: 8.0272. Min Act: -0.1700
Data Index: 8204291 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0897. Min Range: -8.0897
Max Act: 7.9022. Min Act: -0.1700
Data Index: 7917523 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0897. Min Range: -8.0897
Max Act: 7.9022. Min Act: -0.1700
Data Index: 3534206 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0897. Min Range: -8.0897
Max Act: 7.9022. Min Act: -0.1700
Data Index: 7228699 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0897. Min Range: -8.0897
Max Act: 7.7772. Min Act: -0.1700
Data Index: 698290 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0897. Min Range: -8.0897
Max Act: 7.7772. Min Act: -0.1700
Data Index: 4336431 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0897. Min Range: -8.0897
Max Act: 7.7772. Min Act: -0.1700
Data Index: 9096 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0897. Min Range: -8.0897
Max Act: 7.7147. Min Act: -0.1700
Data Index: 7957193 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0897. Min Range: -8.0897
Max Act: 7.7147. Min Act: -0.1700
Data Index: 7918732 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0897. Min Range: -8.0897
Max Act: 7.7147. Min Act: -0.1700
Data Index: 5888044 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0897. Min Range: -8.0897
Max Act: 7.7147. Min Act: -0.1700
Data Index: 1635251 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0897. Min Range: -8.0897
Max Act: 7.7147. Min Act: -0.1700
Data Index: 8333724 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0897. Min Range: -8.0897
Max Act: 7.7147. Min Act: -0.1700
Data Index: 7008039 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0897. Min Range: -8.0897
Max Act: 7.7147. Min Act: -0.1700
Data Index: 5769652 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0897. Min Range: -8.0897
Max Act: 7.7147. Min Act: -0.1700
Data Index: 7454539 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0897. Min Range: -8.0897
Max Act: 7.6522. Min Act: -0.1700
Data Index: 5113150 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0897. Min Range: -8.0897
Max Act: 7.6522. Min Act: -0.1700
Data Index: 794608 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0897. Min Range: -8.0897
Max Act: 7.6522. Min Act: -0.1700
Data Index: 4090184 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #19