Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2644 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4726. Min Range: -8.4726
Max Act: 8.4726. Min Act: -0.1700
Data Index: 8734583 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4726. Min Range: -8.4726
Max Act: 8.2226. Min Act: -0.1700
Data Index: 335159 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4726. Min Range: -8.4726
Max Act: 8.2226. Min Act: -0.1700
Data Index: 7744430 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4726. Min Range: -8.4726
Max Act: 8.1601. Min Act: -0.1700
Data Index: 7090026 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4726. Min Range: -8.4726
Max Act: 8.1601. Min Act: -0.1700
Data Index: 1311761 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4726. Min Range: -8.4726
Max Act: 7.9101. Min Act: -0.1700
Data Index: 3299207 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4726. Min Range: -8.4726
Max Act: 7.9101. Min Act: -0.1700
Data Index: 7923076 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4726. Min Range: -8.4726
Max Act: 7.8476. Min Act: -0.1700
Data Index: 3686830 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4726. Min Range: -8.4726
Max Act: 7.8476. Min Act: -0.1700
Data Index: 5530127 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4726. Min Range: -8.4726
Max Act: 7.8476. Min Act: -0.1700
Data Index: 1094851 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4726. Min Range: -8.4726
Max Act: 7.8476. Min Act: -0.1700
Data Index: 2458965 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4726. Min Range: -8.4726
Max Act: 7.7851. Min Act: -0.1700
Data Index: 7045484 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4726. Min Range: -8.4726
Max Act: 7.7226. Min Act: -0.1700
Data Index: 2512293 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4726. Min Range: -8.4726
Max Act: 7.6913. Min Act: -0.1700
Data Index: 6023629 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4726. Min Range: -8.4726
Max Act: 7.6601. Min Act: -0.1700
Data Index: 7440549 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4726. Min Range: -8.4726
Max Act: 7.5976. Min Act: -0.1700
Data Index: 7494282 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4726. Min Range: -8.4726
Max Act: 7.5976. Min Act: -0.1700
Data Index: 3278759 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4726. Min Range: -8.4726
Max Act: 7.5976. Min Act: -0.1700
Data Index: 7106145 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4726. Min Range: -8.4726
Max Act: 7.5976. Min Act: -0.1700
Data Index: 882632 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4726. Min Range: -8.4726
Max Act: 7.5663. Min Act: -0.1700
Data Index: 4005590 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #19