Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4532 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9023. Min Range: -6.9023
Max Act: 6.9023. Min Act: -0.1700
Data Index: 3067429 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9023. Min Range: -6.9023
Max Act: 6.7148. Min Act: -0.1700
Data Index: 974404 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9023. Min Range: -6.9023
Max Act: 6.6210. Min Act: -0.1700
Data Index: 6951052 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9023. Min Range: -6.9023
Max Act: 6.5585. Min Act: -0.1700
Data Index: 5563238 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9023. Min Range: -6.9023
Max Act: 6.5273. Min Act: -0.1700
Data Index: 2185140 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9023. Min Range: -6.9023
Max Act: 6.5273. Min Act: -0.1700
Data Index: 2255928 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9023. Min Range: -6.9023
Max Act: 6.4960. Min Act: -0.1700
Data Index: 4373206 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9023. Min Range: -6.9023
Max Act: 6.4960. Min Act: -0.1700
Data Index: 1917766 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9023. Min Range: -6.9023
Max Act: 6.4648. Min Act: -0.1700
Data Index: 6611801 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9023. Min Range: -6.9023
Max Act: 6.4648. Min Act: -0.1700
Data Index: 3221985 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9023. Min Range: -6.9023
Max Act: 6.4648. Min Act: -0.1700
Data Index: 4273172 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9023. Min Range: -6.9023
Max Act: 6.4648. Min Act: -0.1700
Data Index: 6597398 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9023. Min Range: -6.9023
Max Act: 6.4648. Min Act: -0.1700
Data Index: 2766636 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9023. Min Range: -6.9023
Max Act: 6.4648. Min Act: -0.1700
Data Index: 5734149 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9023. Min Range: -6.9023
Max Act: 6.4648. Min Act: -0.1700
Data Index: 937796 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9023. Min Range: -6.9023
Max Act: 6.4335. Min Act: -0.1700
Data Index: 5168422 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9023. Min Range: -6.9023
Max Act: 6.4335. Min Act: -0.1700
Data Index: 7533591 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9023. Min Range: -6.9023
Max Act: 6.4335. Min Act: -0.1700
Data Index: 3682723 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9023. Min Range: -6.9023
Max Act: 6.4023. Min Act: -0.1700
Data Index: 696075 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9023. Min Range: -6.9023
Max Act: 6.4335. Min Act: -0.1700
Data Index: 8491563 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #19