Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3090 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.4539. Min Range: -2.4539
Max Act: 2.4539. Min Act: -0.1700
Data Index: 7686056 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4539. Min Range: -2.4539
Max Act: 2.4376. Min Act: -0.1700
Data Index: 6091867 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4539. Min Range: -2.4539
Max Act: 2.4376. Min Act: -0.1700
Data Index: 5010332 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4539. Min Range: -2.4539
Max Act: 2.3887. Min Act: -0.1700
Data Index: 4625620 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4539. Min Range: -2.4539
Max Act: 2.4050. Min Act: -0.1700
Data Index: 1142033 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4539. Min Range: -2.4539
Max Act: 2.3724. Min Act: -0.1700
Data Index: 993404 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4539. Min Range: -2.4539
Max Act: 2.3724. Min Act: -0.1700
Data Index: 7038091 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4539. Min Range: -2.4539
Max Act: 2.3560. Min Act: -0.1700
Data Index: 8628604 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4539. Min Range: -2.4539
Max Act: 2.3560. Min Act: -0.1700
Data Index: 3136936 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4539. Min Range: -2.4539
Max Act: 2.3396. Min Act: -0.1700
Data Index: 6108558 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4539. Min Range: -2.4539
Max Act: 2.3396. Min Act: -0.1700
Data Index: 7357737 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4539. Min Range: -2.4539
Max Act: 2.3232. Min Act: -0.1700
Data Index: 6580940 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4539. Min Range: -2.4539
Max Act: 2.3232. Min Act: -0.1700
Data Index: 7476394 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4539. Min Range: -2.4539
Max Act: 2.3232. Min Act: -0.1700
Data Index: 6439533 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4539. Min Range: -2.4539
Max Act: 2.3068. Min Act: -0.1700
Data Index: 6399981 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4539. Min Range: -2.4539
Max Act: 2.3068. Min Act: -0.1700
Data Index: 1009842 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4539. Min Range: -2.4539
Max Act: 2.3068. Min Act: -0.1700
Data Index: 8616842 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4539. Min Range: -2.4539
Max Act: 2.3232. Min Act: -0.1700
Data Index: 5864539 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4539. Min Range: -2.4539
Max Act: 2.3068. Min Act: -0.1700
Data Index: 3963822 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4539. Min Range: -2.4539
Max Act: 2.2903. Min Act: -0.1700
Data Index: 2843074 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #19