Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4339 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9689. Min Range: -5.9689
Max Act: 5.9689. Min Act: -0.1700
Data Index: 373457 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9689. Min Range: -5.9689
Max Act: 5.8751. Min Act: -0.1700
Data Index: 373470 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9689. Min Range: -5.9689
Max Act: 5.8439. Min Act: -0.1700
Data Index: 3794335 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9689. Min Range: -5.9689
Max Act: 5.7189. Min Act: -0.1700
Data Index: 518099 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9689. Min Range: -5.9689
Max Act: 5.6564. Min Act: -0.1700
Data Index: 4015103 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9689. Min Range: -5.9689
Max Act: 5.6251. Min Act: -0.1700
Data Index: 8384680 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9689. Min Range: -5.9689
Max Act: 5.6251. Min Act: -0.1700
Data Index: 8383718 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9689. Min Range: -5.9689
Max Act: 5.5939. Min Act: -0.1700
Data Index: 8067309 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9689. Min Range: -5.9689
Max Act: 5.5939. Min Act: -0.1700
Data Index: 4970918 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9689. Min Range: -5.9689
Max Act: 5.5939. Min Act: -0.1700
Data Index: 5520987 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9689. Min Range: -5.9689
Max Act: 5.5939. Min Act: -0.1700
Data Index: 1998158 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9689. Min Range: -5.9689
Max Act: 5.5626. Min Act: -0.1700
Data Index: 4373744 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9689. Min Range: -5.9689
Max Act: 5.5626. Min Act: -0.1700
Data Index: 6611448 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9689. Min Range: -5.9689
Max Act: 5.5314. Min Act: -0.1700
Data Index: 8750948 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9689. Min Range: -5.9689
Max Act: 5.5314. Min Act: -0.1700
Data Index: 6062428 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9689. Min Range: -5.9689
Max Act: 5.5314. Min Act: -0.1700
Data Index: 311749 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9689. Min Range: -5.9689
Max Act: 5.5314. Min Act: -0.1700
Data Index: 4582650 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9689. Min Range: -5.9689
Max Act: 5.5314. Min Act: -0.1700
Data Index: 6634750 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9689. Min Range: -5.9689
Max Act: 5.5001. Min Act: -0.1700
Data Index: 2134560 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9689. Min Range: -5.9689
Max Act: 5.5001. Min Act: -0.1700
Data Index: 1055796 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #19