Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4398 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5785. Min Range: -5.5785
Max Act: 5.5785. Min Act: -0.1700
Data Index: 4725367 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5785. Min Range: -5.5785
Max Act: 5.4847. Min Act: -0.1700
Data Index: 1116432 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5785. Min Range: -5.5785
Max Act: 5.3910. Min Act: -0.1700
Data Index: 5311917 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5785. Min Range: -5.5785
Max Act: 5.3597. Min Act: -0.1700
Data Index: 5391945 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5785. Min Range: -5.5785
Max Act: 5.3597. Min Act: -0.1700
Data Index: 5853048 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5785. Min Range: -5.5785
Max Act: 5.3597. Min Act: -0.1700
Data Index: 7910601 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5785. Min Range: -5.5785
Max Act: 5.3285. Min Act: -0.1700
Data Index: 1031986 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5785. Min Range: -5.5785
Max Act: 5.3285. Min Act: -0.1700
Data Index: 3983232 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5785. Min Range: -5.5785
Max Act: 5.3285. Min Act: -0.1700
Data Index: 1890631 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5785. Min Range: -5.5785
Max Act: 5.2972. Min Act: -0.1700
Data Index: 2926136 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5785. Min Range: -5.5785
Max Act: 5.3285. Min Act: -0.1700
Data Index: 5831938 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5785. Min Range: -5.5785
Max Act: 5.2972. Min Act: -0.1700
Data Index: 543898 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5785. Min Range: -5.5785
Max Act: 5.2347. Min Act: -0.1700
Data Index: 2054435 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5785. Min Range: -5.5785
Max Act: 5.2347. Min Act: -0.1700
Data Index: 6363782 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5785. Min Range: -5.5785
Max Act: 5.2347. Min Act: -0.1700
Data Index: 5081607 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5785. Min Range: -5.5785
Max Act: 5.2035. Min Act: -0.1700
Data Index: 2030126 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5785. Min Range: -5.5785
Max Act: 5.2035. Min Act: -0.1700
Data Index: 7763501 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5785. Min Range: -5.5785
Max Act: 5.2035. Min Act: -0.1700
Data Index: 2954035 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5785. Min Range: -5.5785
Max Act: 5.2035. Min Act: -0.1700
Data Index: 4695709 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5785. Min Range: -5.5785
Max Act: 5.1722. Min Act: -0.1700
Data Index: 1832303 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #19