Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4678 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3783. Min Range: -6.3783
Max Act: 6.3783. Min Act: -0.1700
Data Index: 8381487 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3783. Min Range: -6.3783
Max Act: 6.2533. Min Act: -0.1700
Data Index: 5073350 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3783. Min Range: -6.3783
Max Act: 6.2533. Min Act: -0.1700
Data Index: 8178933 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3783. Min Range: -6.3783
Max Act: 6.0971. Min Act: -0.1700
Data Index: 508485 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3783. Min Range: -6.3783
Max Act: 6.0658. Min Act: -0.1700
Data Index: 5137164 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3783. Min Range: -6.3783
Max Act: 6.0346. Min Act: -0.1700
Data Index: 7684866 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3783. Min Range: -6.3783
Max Act: 6.0346. Min Act: -0.1700
Data Index: 8831503 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3783. Min Range: -6.3783
Max Act: 6.0346. Min Act: -0.1700
Data Index: 4732830 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3783. Min Range: -6.3783
Max Act: 6.0033. Min Act: -0.1700
Data Index: 6086003 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3783. Min Range: -6.3783
Max Act: 5.9721. Min Act: -0.1700
Data Index: 1868642 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3783. Min Range: -6.3783
Max Act: 5.9721. Min Act: -0.1700
Data Index: 2721451 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3783. Min Range: -6.3783
Max Act: 5.9096. Min Act: -0.1700
Data Index: 6958122 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3783. Min Range: -6.3783
Max Act: 5.9096. Min Act: -0.1700
Data Index: 2549849 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3783. Min Range: -6.3783
Max Act: 5.9096. Min Act: -0.1700
Data Index: 4006950 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3783. Min Range: -6.3783
Max Act: 5.8471. Min Act: -0.1700
Data Index: 523099 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3783. Min Range: -6.3783
Max Act: 5.8783. Min Act: -0.1700
Data Index: 7556103 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3783. Min Range: -6.3783
Max Act: 5.8783. Min Act: -0.1700
Data Index: 4824536 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3783. Min Range: -6.3783
Max Act: 5.8783. Min Act: -0.1700
Data Index: 3348796 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3783. Min Range: -6.3783
Max Act: 5.8471. Min Act: -0.1700
Data Index: 4547958 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3783. Min Range: -6.3783
Max Act: 5.8471. Min Act: -0.1700
Data Index: 4417310 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #19