Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2553 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.8209. Min Range: -5.8209
Max Act: 5.8209. Min Act: -0.1700
Data Index: 4268681 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8209. Min Range: -5.8209
Max Act: 5.7584. Min Act: -0.1700
Data Index: 8015730 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8209. Min Range: -5.8209
Max Act: 5.6959. Min Act: -0.1700
Data Index: 8135100 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8209. Min Range: -5.8209
Max Act: 5.6021. Min Act: -0.1700
Data Index: 8347813 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8209. Min Range: -5.8209
Max Act: 5.5084. Min Act: -0.1700
Data Index: 4134968 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8209. Min Range: -5.8209
Max Act: 5.5084. Min Act: -0.1700
Data Index: 1971367 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8209. Min Range: -5.8209
Max Act: 5.4771. Min Act: -0.1700
Data Index: 4143000 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8209. Min Range: -5.8209
Max Act: 5.4771. Min Act: -0.1700
Data Index: 3441382 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8209. Min Range: -5.8209
Max Act: 5.5084. Min Act: -0.1700
Data Index: 8564791 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8209. Min Range: -5.8209
Max Act: 5.4146. Min Act: -0.1700
Data Index: 3876128 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8209. Min Range: -5.8209
Max Act: 5.4146. Min Act: -0.1700
Data Index: 6292324 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8209. Min Range: -5.8209
Max Act: 5.4146. Min Act: -0.1700
Data Index: 4053153 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8209. Min Range: -5.8209
Max Act: 5.4146. Min Act: -0.1700
Data Index: 2501901 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8209. Min Range: -5.8209
Max Act: 5.4146. Min Act: -0.1700
Data Index: 5205583 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8209. Min Range: -5.8209
Max Act: 5.3834. Min Act: -0.1700
Data Index: 1287037 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8209. Min Range: -5.8209
Max Act: 5.3521. Min Act: -0.1700
Data Index: 43095 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8209. Min Range: -5.8209
Max Act: 5.3521. Min Act: -0.1700
Data Index: 8135101 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8209. Min Range: -5.8209
Max Act: 5.3521. Min Act: -0.1700
Data Index: 5589837 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8209. Min Range: -5.8209
Max Act: 5.3521. Min Act: -0.1700
Data Index: 7960661 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8209. Min Range: -5.8209
Max Act: 5.3521. Min Act: -0.1700
Data Index: 7070521 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #19