Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4632 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7570. Min Range: -5.7570
Max Act: 5.7570. Min Act: -0.1700
Data Index: 7669182 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7570. Min Range: -5.7570
Max Act: 5.6320. Min Act: -0.1700
Data Index: 5107257 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7570. Min Range: -5.7570
Max Act: 5.5695. Min Act: -0.1700
Data Index: 489329 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7570. Min Range: -5.7570
Max Act: 5.5383. Min Act: -0.1699
Data Index: 3881570 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7570. Min Range: -5.7570
Max Act: 5.5070. Min Act: -0.1700
Data Index: 4239166 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7570. Min Range: -5.7570
Max Act: 5.5070. Min Act: -0.1700
Data Index: 4883035 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7570. Min Range: -5.7570
Max Act: 5.4758. Min Act: -0.1700
Data Index: 33852 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7570. Min Range: -5.7570
Max Act: 5.4445. Min Act: -0.1700
Data Index: 989915 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7570. Min Range: -5.7570
Max Act: 5.3820. Min Act: -0.1697
Data Index: 623325 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7570. Min Range: -5.7570
Max Act: 5.3820. Min Act: -0.1700
Data Index: 5076985 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7570. Min Range: -5.7570
Max Act: 5.3508. Min Act: -0.1700
Data Index: 2976648 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7570. Min Range: -5.7570
Max Act: 5.3508. Min Act: -0.1700
Data Index: 5826791 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7570. Min Range: -5.7570
Max Act: 5.3508. Min Act: -0.1700
Data Index: 8497721 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7570. Min Range: -5.7570
Max Act: 5.2883. Min Act: -0.1700
Data Index: 2256478 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7570. Min Range: -5.7570
Max Act: 5.3508. Min Act: -0.1700
Data Index: 8772920 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7570. Min Range: -5.7570
Max Act: 5.3195. Min Act: -0.1700
Data Index: 8399131 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7570. Min Range: -5.7570
Max Act: 5.3195. Min Act: -0.1697
Data Index: 6243600 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7570. Min Range: -5.7570
Max Act: 5.3195. Min Act: -0.1700
Data Index: 5620094 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7570. Min Range: -5.7570
Max Act: 5.2570. Min Act: -0.1700
Data Index: 7982581 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7570. Min Range: -5.7570
Max Act: 5.2883. Min Act: -0.1700
Data Index: 1829200 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #19