Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3489 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.2485. Min Range: -2.2485
Max Act: 2.2485. Min Act: -0.1700
Data Index: 7865673 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2485. Min Range: -2.2485
Max Act: 2.0988. Min Act: -0.1700
Data Index: 5984464 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2485. Min Range: -2.2485
Max Act: 2.0148. Min Act: -0.1700
Data Index: 8476400 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2485. Min Range: -2.2485
Max Act: 2.0148. Min Act: -0.1700
Data Index: 5738294 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2485. Min Range: -2.2485
Max Act: 1.9470. Min Act: -0.1700
Data Index: 1318300 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2485. Min Range: -2.2485
Max Act: 1.9470. Min Act: -0.1700
Data Index: 4993229 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2485. Min Range: -2.2485
Max Act: 1.9130. Min Act: -0.1700
Data Index: 42923 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2485. Min Range: -2.2485
Max Act: 1.8447. Min Act: -0.1700
Data Index: 8658684 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2485. Min Range: -2.2485
Max Act: 1.8789. Min Act: -0.1700
Data Index: 5312189 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2485. Min Range: -2.2485
Max Act: 1.7587. Min Act: -0.1700
Data Index: 1587241 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2485. Min Range: -2.2485
Max Act: 1.7587. Min Act: -0.1700
Data Index: 2531066 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2485. Min Range: -2.2485
Max Act: 1.6894. Min Act: -0.1700
Data Index: 6437133 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2485. Min Range: -2.2485
Max Act: 1.6721. Min Act: -0.1700
Data Index: 8162053 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2485. Min Range: -2.2485
Max Act: 1.6894. Min Act: -0.1700
Data Index: 3384923 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2485. Min Range: -2.2485
Max Act: 1.6547. Min Act: -0.1700
Data Index: 5673722 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2485. Min Range: -2.2485
Max Act: 1.6547. Min Act: -0.1700
Data Index: 5547582 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2485. Min Range: -2.2485
Max Act: 1.6373. Min Act: -0.1700
Data Index: 1186684 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2485. Min Range: -2.2485
Max Act: 1.6373. Min Act: -0.1700
Data Index: 32960 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2485. Min Range: -2.2485
Max Act: 1.6198. Min Act: -0.1700
Data Index: 2970039 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2485. Min Range: -2.2485
Max Act: 1.6198. Min Act: -0.1700
Data Index: 7913474 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #19