Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2781 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.5087. Min Range: -8.5087
Max Act: 8.4462. Min Act: -0.1700
Data Index: 1402092 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5087. Min Range: -8.5087
Max Act: 8.5087. Min Act: -0.1700
Data Index: 7386429 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5087. Min Range: -8.5087
Max Act: 8.3837. Min Act: -0.1700
Data Index: 951386 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5087. Min Range: -8.5087
Max Act: 8.3837. Min Act: -0.1700
Data Index: 2164655 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5087. Min Range: -8.5087
Max Act: 8.2275. Min Act: -0.1700
Data Index: 3412518 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5087. Min Range: -8.5087
Max Act: 8.1962. Min Act: -0.1700
Data Index: 1426127 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5087. Min Range: -8.5087
Max Act: 8.1650. Min Act: -0.1700
Data Index: 5218369 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5087. Min Range: -8.5087
Max Act: 8.1650. Min Act: -0.1700
Data Index: 2834987 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5087. Min Range: -8.5087
Max Act: 8.0400. Min Act: -0.1700
Data Index: 7859508 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5087. Min Range: -8.5087
Max Act: 7.9462. Min Act: -0.1700
Data Index: 2884610 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5087. Min Range: -8.5087
Max Act: 7.8837. Min Act: -0.1700
Data Index: 7471401 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5087. Min Range: -8.5087
Max Act: 7.8837. Min Act: -0.1700
Data Index: 7788595 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5087. Min Range: -8.5087
Max Act: 7.8212. Min Act: -0.1700
Data Index: 5548565 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5087. Min Range: -8.5087
Max Act: 7.8212. Min Act: -0.1700
Data Index: 6993881 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5087. Min Range: -8.5087
Max Act: 7.8525. Min Act: -0.1700
Data Index: 3065691 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5087. Min Range: -8.5087
Max Act: 7.7900. Min Act: -0.1700
Data Index: 4095390 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5087. Min Range: -8.5087
Max Act: 7.7587. Min Act: -0.1700
Data Index: 7249206 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5087. Min Range: -8.5087
Max Act: 7.7587. Min Act: -0.1700
Data Index: 3101540 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5087. Min Range: -8.5087
Max Act: 7.7275. Min Act: -0.1700
Data Index: 7620331 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5087. Min Range: -8.5087
Max Act: 7.6962. Min Act: -0.1700
Data Index: 5376248 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #19