Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3843 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3726. Min Range: -6.3726
Max Act: 6.3726. Min Act: -0.1700
Data Index: 3484071 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3726. Min Range: -6.3726
Max Act: 5.9976. Min Act: -0.1700
Data Index: 1382650 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3726. Min Range: -6.3726
Max Act: 5.9351. Min Act: -0.1700
Data Index: 406661 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3726. Min Range: -6.3726
Max Act: 5.8726. Min Act: -0.1700
Data Index: 6683658 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3726. Min Range: -6.3726
Max Act: 5.8413. Min Act: -0.1700
Data Index: 6338594 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3726. Min Range: -6.3726
Max Act: 5.8413. Min Act: -0.1700
Data Index: 8544180 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3726. Min Range: -6.3726
Max Act: 5.7163. Min Act: -0.1700
Data Index: 3529391 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3726. Min Range: -6.3726
Max Act: 5.7163. Min Act: -0.1700
Data Index: 6980691 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3726. Min Range: -6.3726
Max Act: 5.7476. Min Act: -0.1700
Data Index: 1529374 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3726. Min Range: -6.3726
Max Act: 5.7163. Min Act: -0.1700
Data Index: 2158055 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3726. Min Range: -6.3726
Max Act: 5.6538. Min Act: -0.1700
Data Index: 3795306 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3726. Min Range: -6.3726
Max Act: 5.6851. Min Act: -0.1700
Data Index: 5169301 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3726. Min Range: -6.3726
Max Act: 5.6851. Min Act: -0.1700
Data Index: 1665421 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3726. Min Range: -6.3726
Max Act: 5.6851. Min Act: -0.1700
Data Index: 5437323 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3726. Min Range: -6.3726
Max Act: 5.6538. Min Act: -0.1700
Data Index: 7652316 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3726. Min Range: -6.3726
Max Act: 5.6538. Min Act: -0.1700
Data Index: 6104261 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3726. Min Range: -6.3726
Max Act: 5.6538. Min Act: -0.1700
Data Index: 84315 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3726. Min Range: -6.3726
Max Act: 5.6226. Min Act: -0.1700
Data Index: 3648576 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3726. Min Range: -6.3726
Max Act: 5.6538. Min Act: -0.1700
Data Index: 1470052 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3726. Min Range: -6.3726
Max Act: 5.6226. Min Act: -0.1700
Data Index: 6131316 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #19