Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 592 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.5953. Min Range: -2.5953
Max Act: 2.5953. Min Act: -0.1700
Data Index: 6218073 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5953. Min Range: -2.5953
Max Act: 2.5146. Min Act: -0.1700
Data Index: 8563217 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5953. Min Range: -2.5953
Max Act: 2.4822. Min Act: -0.1700
Data Index: 5333351 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5953. Min Range: -2.5953
Max Act: 2.4498. Min Act: -0.1700
Data Index: 3955244 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5953. Min Range: -2.5953
Max Act: 2.5146. Min Act: -0.1700
Data Index: 1050758 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5953. Min Range: -2.5953
Max Act: 2.4822. Min Act: -0.1700
Data Index: 7684398 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5953. Min Range: -2.5953
Max Act: 2.4498. Min Act: -0.1700
Data Index: 4205018 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5953. Min Range: -2.5953
Max Act: 2.4498. Min Act: -0.1700
Data Index: 4379437 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5953. Min Range: -2.5953
Max Act: 2.4822. Min Act: -0.1700
Data Index: 3793160 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5953. Min Range: -2.5953
Max Act: 2.4335. Min Act: -0.1700
Data Index: 4963944 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5953. Min Range: -2.5953
Max Act: 2.4335. Min Act: -0.1700
Data Index: 7340643 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5953. Min Range: -2.5953
Max Act: 2.4335. Min Act: -0.1700
Data Index: 1086757 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5953. Min Range: -2.5953
Max Act: 2.4498. Min Act: -0.1700
Data Index: 5378506 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5953. Min Range: -2.5953
Max Act: 2.4172. Min Act: -0.1700
Data Index: 4147027 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5953. Min Range: -2.5953
Max Act: 2.4009. Min Act: -0.1700
Data Index: 769317 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5953. Min Range: -2.5953
Max Act: 2.4172. Min Act: -0.1700
Data Index: 2787742 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5953. Min Range: -2.5953
Max Act: 2.4009. Min Act: -0.1700
Data Index: 7170948 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5953. Min Range: -2.5953
Max Act: 2.3518. Min Act: -0.1700
Data Index: 4889768 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5953. Min Range: -2.5953
Max Act: 2.4009. Min Act: -0.1700
Data Index: 8641089 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5953. Min Range: -2.5953
Max Act: 2.4009. Min Act: -0.1700
Data Index: 155510 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #19