Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2983 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5343. Min Range: -4.5343
Max Act: 4.5343. Min Act: -0.1700
Data Index: 7847765 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5343. Min Range: -4.5343
Max Act: 4.1906. Min Act: -0.1700
Data Index: 2342651 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5343. Min Range: -4.5343
Max Act: 4.0655. Min Act: -0.1700
Data Index: 3099125 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5343. Min Range: -4.5343
Max Act: 4.0343. Min Act: -0.1700
Data Index: 6857736 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5343. Min Range: -4.5343
Max Act: 3.9718. Min Act: -0.1700
Data Index: 4702508 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5343. Min Range: -4.5343
Max Act: 3.9718. Min Act: -0.1700
Data Index: 1359926 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5343. Min Range: -4.5343
Max Act: 3.9405. Min Act: -0.1700
Data Index: 2191595 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5343. Min Range: -4.5343
Max Act: 3.9249. Min Act: -0.1700
Data Index: 4101043 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5343. Min Range: -4.5343
Max Act: 3.8936. Min Act: -0.1700
Data Index: 2128377 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5343. Min Range: -4.5343
Max Act: 3.8936. Min Act: -0.1700
Data Index: 6160739 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5343. Min Range: -4.5343
Max Act: 3.8780. Min Act: -0.1700
Data Index: 7134193 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5343. Min Range: -4.5343
Max Act: 3.8780. Min Act: -0.1700
Data Index: 8672775 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5343. Min Range: -4.5343
Max Act: 3.8623. Min Act: -0.1700
Data Index: 6722534 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5343. Min Range: -4.5343
Max Act: 3.8780. Min Act: -0.1700
Data Index: 2679583 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5343. Min Range: -4.5343
Max Act: 3.8623. Min Act: -0.1700
Data Index: 2964582 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5343. Min Range: -4.5343
Max Act: 3.8780. Min Act: -0.1700
Data Index: 2185438 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5343. Min Range: -4.5343
Max Act: 3.8780. Min Act: -0.1700
Data Index: 6409312 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5343. Min Range: -4.5343
Max Act: 3.8623. Min Act: -0.1700
Data Index: 4666374 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5343. Min Range: -4.5343
Max Act: 3.8623. Min Act: -0.1700
Data Index: 4250145 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5343. Min Range: -4.5343
Max Act: 3.8623. Min Act: -0.1700
Data Index: 2834113 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #19