Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2495 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8866. Min Range: -5.8866
Max Act: 5.8866. Min Act: -0.1700
Data Index: 3925262 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8866. Min Range: -5.8866
Max Act: 5.8866. Min Act: -0.1700
Data Index: 368047 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8866. Min Range: -5.8866
Max Act: 5.8241. Min Act: -0.1700
Data Index: 8680782 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8866. Min Range: -5.8866
Max Act: 5.8241. Min Act: -0.1700
Data Index: 7139689 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8866. Min Range: -5.8866
Max Act: 5.8241. Min Act: -0.1700
Data Index: 8754133 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8866. Min Range: -5.8866
Max Act: 5.7929. Min Act: -0.1700
Data Index: 5789738 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8866. Min Range: -5.8866
Max Act: 5.8241. Min Act: -0.1700
Data Index: 758857 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8866. Min Range: -5.8866
Max Act: 5.7616. Min Act: -0.1700
Data Index: 4221678 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8866. Min Range: -5.8866
Max Act: 5.7304. Min Act: -0.1700
Data Index: 8744111 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8866. Min Range: -5.8866
Max Act: 5.7304. Min Act: -0.1700
Data Index: 2658920 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8866. Min Range: -5.8866
Max Act: 5.6991. Min Act: -0.1700
Data Index: 2999166 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8866. Min Range: -5.8866
Max Act: 5.6366. Min Act: -0.1700
Data Index: 1626132 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8866. Min Range: -5.8866
Max Act: 5.6679. Min Act: -0.1700
Data Index: 2975207 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8866. Min Range: -5.8866
Max Act: 5.6679. Min Act: -0.1700
Data Index: 7966434 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8866. Min Range: -5.8866
Max Act: 5.6679. Min Act: -0.1700
Data Index: 4171702 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8866. Min Range: -5.8866
Max Act: 5.6679. Min Act: -0.1700
Data Index: 1394695 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8866. Min Range: -5.8866
Max Act: 5.6366. Min Act: -0.1700
Data Index: 5693954 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8866. Min Range: -5.8866
Max Act: 5.6366. Min Act: -0.1700
Data Index: 2004501 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8866. Min Range: -5.8866
Max Act: 5.5429. Min Act: -0.1700
Data Index: 5970347 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8866. Min Range: -5.8866
Max Act: 5.5741. Min Act: -0.1700
Data Index: 2046412 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #19