Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3431 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3894. Min Range: -3.3894
Max Act: 3.3894. Min Act: -0.1700
Data Index: 2766811 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3894. Min Range: -3.3894
Max Act: 3.3580. Min Act: -0.1700
Data Index: 6890831 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3894. Min Range: -3.3894
Max Act: 3.3580. Min Act: -0.1700
Data Index: 1929713 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3894. Min Range: -3.3894
Max Act: 3.3267. Min Act: -0.1700
Data Index: 6317700 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3894. Min Range: -3.3894
Max Act: 3.2953. Min Act: -0.1700
Data Index: 4265448 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3894. Min Range: -3.3894
Max Act: 3.2953. Min Act: -0.1700
Data Index: 987163 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3894. Min Range: -3.3894
Max Act: 3.2953. Min Act: -0.1700
Data Index: 7615688 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3894. Min Range: -3.3894
Max Act: 3.2953. Min Act: -0.1700
Data Index: 8685553 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3894. Min Range: -3.3894
Max Act: 3.2953. Min Act: -0.1700
Data Index: 2197782 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3894. Min Range: -3.3894
Max Act: 3.2953. Min Act: -0.1700
Data Index: 6244832 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3894. Min Range: -3.3894
Max Act: 3.2639. Min Act: -0.1700
Data Index: 3309322 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3894. Min Range: -3.3894
Max Act: 3.2639. Min Act: -0.1700
Data Index: 6351834 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3894. Min Range: -3.3894
Max Act: 3.2639. Min Act: -0.1700
Data Index: 6317693 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3894. Min Range: -3.3894
Max Act: 3.2639. Min Act: -0.1700
Data Index: 2706351 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3894. Min Range: -3.3894
Max Act: 3.2639. Min Act: -0.1700
Data Index: 5885785 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3894. Min Range: -3.3894
Max Act: 3.2639. Min Act: -0.1700
Data Index: 5872234 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3894. Min Range: -3.3894
Max Act: 3.2639. Min Act: -0.1700
Data Index: 5326379 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3894. Min Range: -3.3894
Max Act: 3.2639. Min Act: -0.1700
Data Index: 1397277 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3894. Min Range: -3.3894
Max Act: 3.2639. Min Act: -0.1700
Data Index: 5249063 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3894. Min Range: -3.3894
Max Act: 3.2639. Min Act: -0.1700
Data Index: 407602 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19