Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 926 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9756. Min Range: -5.9756
Max Act: 5.9444. Min Act: -0.1700
Data Index: 1586323 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9756. Min Range: -5.9756
Max Act: 5.9756. Min Act: -0.1700
Data Index: 5978382 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9756. Min Range: -5.9756
Max Act: 5.9444. Min Act: -0.1700
Data Index: 3165115 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9756. Min Range: -5.9756
Max Act: 5.9131. Min Act: -0.1700
Data Index: 8699216 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9756. Min Range: -5.9756
Max Act: 5.9131. Min Act: -0.1700
Data Index: 527468 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9756. Min Range: -5.9756
Max Act: 5.7881. Min Act: -0.1700
Data Index: 667488 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9756. Min Range: -5.9756
Max Act: 5.6944. Min Act: -0.1700
Data Index: 957025 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9756. Min Range: -5.9756
Max Act: 5.6944. Min Act: -0.1700
Data Index: 334401 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9756. Min Range: -5.9756
Max Act: 5.6631. Min Act: -0.1700
Data Index: 6385958 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9756. Min Range: -5.9756
Max Act: 5.5694. Min Act: -0.1700
Data Index: 692352 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9756. Min Range: -5.9756
Max Act: 5.6006. Min Act: -0.1700
Data Index: 7174086 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9756. Min Range: -5.9756
Max Act: 5.5381. Min Act: -0.1700
Data Index: 7777192 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9756. Min Range: -5.9756
Max Act: 5.5694. Min Act: -0.1700
Data Index: 585038 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9756. Min Range: -5.9756
Max Act: 5.5694. Min Act: -0.1700
Data Index: 3460666 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9756. Min Range: -5.9756
Max Act: 5.5069. Min Act: -0.1700
Data Index: 3720784 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9756. Min Range: -5.9756
Max Act: 5.4444. Min Act: -0.1700
Data Index: 7187810 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9756. Min Range: -5.9756
Max Act: 5.4444. Min Act: -0.1700
Data Index: 1736269 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9756. Min Range: -5.9756
Max Act: 5.3819. Min Act: -0.1700
Data Index: 7868908 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9756. Min Range: -5.9756
Max Act: 5.3819. Min Act: -0.1700
Data Index: 4782281 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9756. Min Range: -5.9756
Max Act: 5.3506. Min Act: -0.1700
Data Index: 2467570 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #19