Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6345 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7621. Min Range: -4.7621
Max Act: 4.7621. Min Act: -0.1700
Data Index: 5058000 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7621. Min Range: -4.7621
Max Act: 4.7621. Min Act: -0.1700
Data Index: 5772717 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7621. Min Range: -4.7621
Max Act: 4.6371. Min Act: -0.1700
Data Index: 2039713 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7621. Min Range: -4.7621
Max Act: 4.4809. Min Act: -0.1700
Data Index: 4983591 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7621. Min Range: -4.7621
Max Act: 4.4496. Min Act: -0.1700
Data Index: 6440620 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7621. Min Range: -4.7621
Max Act: 4.4184. Min Act: -0.1700
Data Index: 2436962 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7621. Min Range: -4.7621
Max Act: 4.3871. Min Act: -0.1700
Data Index: 6512114 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7621. Min Range: -4.7621
Max Act: 4.3559. Min Act: -0.1700
Data Index: 1370686 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7621. Min Range: -4.7621
Max Act: 4.3871. Min Act: -0.1700
Data Index: 4279839 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7621. Min Range: -4.7621
Max Act: 4.2934. Min Act: -0.1700
Data Index: 5603280 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7621. Min Range: -4.7621
Max Act: 4.2621. Min Act: -0.1700
Data Index: 6602556 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7621. Min Range: -4.7621
Max Act: 4.2621. Min Act: -0.1700
Data Index: 6919304 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7621. Min Range: -4.7621
Max Act: 4.1996. Min Act: -0.1700
Data Index: 555346 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7621. Min Range: -4.7621
Max Act: 4.2309. Min Act: -0.1700
Data Index: 7512599 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7621. Min Range: -4.7621
Max Act: 4.1996. Min Act: -0.1700
Data Index: 8567056 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7621. Min Range: -4.7621
Max Act: 4.2309. Min Act: -0.1700
Data Index: 2916713 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7621. Min Range: -4.7621
Max Act: 4.1996. Min Act: -0.1700
Data Index: 8254238 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7621. Min Range: -4.7621
Max Act: 4.1996. Min Act: -0.1700
Data Index: 7446052 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7621. Min Range: -4.7621
Max Act: 4.1996. Min Act: -0.1700
Data Index: 8095772 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7621. Min Range: -4.7621
Max Act: 4.1996. Min Act: -0.1700
Data Index: 8421328 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #19