Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3404 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8495. Min Range: -6.8495
Max Act: 6.8495. Min Act: -0.1700
Data Index: 8649148 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8495. Min Range: -6.8495
Max Act: 6.5995. Min Act: -0.1700
Data Index: 8401921 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8495. Min Range: -6.8495
Max Act: 6.5683. Min Act: -0.1700
Data Index: 8541497 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8495. Min Range: -6.8495
Max Act: 6.5370. Min Act: -0.1700
Data Index: 5432146 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8495. Min Range: -6.8495
Max Act: 6.4745. Min Act: -0.1700
Data Index: 921972 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8495. Min Range: -6.8495
Max Act: 6.4433. Min Act: -0.1700
Data Index: 4093803 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8495. Min Range: -6.8495
Max Act: 6.4745. Min Act: -0.1700
Data Index: 2442187 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8495. Min Range: -6.8495
Max Act: 6.4120. Min Act: -0.1700
Data Index: 214281 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8495. Min Range: -6.8495
Max Act: 6.3183. Min Act: -0.1700
Data Index: 1830097 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8495. Min Range: -6.8495
Max Act: 6.3495. Min Act: -0.1700
Data Index: 1999430 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8495. Min Range: -6.8495
Max Act: 6.3183. Min Act: -0.1700
Data Index: 283360 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8495. Min Range: -6.8495
Max Act: 6.3183. Min Act: -0.1700
Data Index: 4640532 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8495. Min Range: -6.8495
Max Act: 6.2558. Min Act: -0.1700
Data Index: 3930030 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8495. Min Range: -6.8495
Max Act: 6.2558. Min Act: -0.1700
Data Index: 1174727 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8495. Min Range: -6.8495
Max Act: 6.2558. Min Act: -0.1700
Data Index: 23210 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8495. Min Range: -6.8495
Max Act: 6.2870. Min Act: -0.1700
Data Index: 8291808 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8495. Min Range: -6.8495
Max Act: 6.2558. Min Act: -0.1700
Data Index: 2399625 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8495. Min Range: -6.8495
Max Act: 6.2245. Min Act: -0.1700
Data Index: 1263075 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8495. Min Range: -6.8495
Max Act: 6.1933. Min Act: -0.1700
Data Index: 6346644 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8495. Min Range: -6.8495
Max Act: 6.2245. Min Act: -0.1700
Data Index: 898597 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #19