Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3399 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.7660. Min Range: -2.7660
Max Act: 2.7660. Min Act: -0.1700
Data Index: 3056729 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7660. Min Range: -2.7660
Max Act: 2.7341. Min Act: -0.1700
Data Index: 3055689 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7660. Min Range: -2.7660
Max Act: 2.7341. Min Act: -0.1700
Data Index: 4674276 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7660. Min Range: -2.7660
Max Act: 2.7341. Min Act: -0.1700
Data Index: 941020 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7660. Min Range: -2.7660
Max Act: 2.7021. Min Act: -0.1700
Data Index: 7079550 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7660. Min Range: -2.7660
Max Act: 2.7021. Min Act: -0.1700
Data Index: 8038549 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7660. Min Range: -2.7660
Max Act: 2.6701. Min Act: -0.1700
Data Index: 3146447 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7660. Min Range: -2.7660
Max Act: 2.6861. Min Act: -0.1700
Data Index: 4058377 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7660. Min Range: -2.7660
Max Act: 2.7021. Min Act: -0.1700
Data Index: 2092980 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7660. Min Range: -2.7660
Max Act: 2.6701. Min Act: -0.1700
Data Index: 8151562 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7660. Min Range: -2.7660
Max Act: 2.6701. Min Act: -0.1700
Data Index: 6755683 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7660. Min Range: -2.7660
Max Act: 2.6701. Min Act: -0.1700
Data Index: 4596335 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7660. Min Range: -2.7660
Max Act: 2.6540. Min Act: -0.1700
Data Index: 116757 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7660. Min Range: -2.7660
Max Act: 2.6380. Min Act: -0.1700
Data Index: 7570142 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7660. Min Range: -2.7660
Max Act: 2.6219. Min Act: -0.1700
Data Index: 52290 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7660. Min Range: -2.7660
Max Act: 2.6219. Min Act: -0.1700
Data Index: 6755682 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7660. Min Range: -2.7660
Max Act: 2.6380. Min Act: -0.1700
Data Index: 5910596 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7660. Min Range: -2.7660
Max Act: 2.6058. Min Act: -0.1700
Data Index: 3553000 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7660. Min Range: -2.7660
Max Act: 2.6058. Min Act: -0.1700
Data Index: 3731941 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7660. Min Range: -2.7660
Max Act: 2.5897. Min Act: -0.1700
Data Index: 4669898 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #19