Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3240 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.0162. Min Range: -2.0162
Max Act: 2.0162. Min Act: -0.1700
Data Index: 4734189 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0162. Min Range: -2.0162
Max Act: 1.8118. Min Act: -0.1700
Data Index: 2154505 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0162. Min Range: -2.0162
Max Act: 1.7688. Min Act: -0.1700
Data Index: 2497588 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0162. Min Range: -2.0162
Max Act: 1.7860. Min Act: -0.1700
Data Index: 5145015 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0162. Min Range: -2.0162
Max Act: 1.7429. Min Act: -0.1700
Data Index: 4075613 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0162. Min Range: -2.0162
Max Act: 1.7256. Min Act: -0.1700
Data Index: 2747095 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0162. Min Range: -2.0162
Max Act: 1.7169. Min Act: -0.1700
Data Index: 8447389 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0162. Min Range: -2.0162
Max Act: 1.7169. Min Act: -0.1700
Data Index: 1099890 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0162. Min Range: -2.0162
Max Act: 1.6909. Min Act: -0.1700
Data Index: 2898836 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0162. Min Range: -2.0162
Max Act: 1.7083. Min Act: -0.1700
Data Index: 4588066 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0162. Min Range: -2.0162
Max Act: 1.6909. Min Act: -0.1700
Data Index: 2521953 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0162. Min Range: -2.0162
Max Act: 1.6909. Min Act: -0.1700
Data Index: 5203785 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0162. Min Range: -2.0162
Max Act: 1.6823. Min Act: -0.1700
Data Index: 8301034 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0162. Min Range: -2.0162
Max Act: 1.6649. Min Act: -0.1700
Data Index: 5151673 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0162. Min Range: -2.0162
Max Act: 1.6736. Min Act: -0.1700
Data Index: 8475040 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0162. Min Range: -2.0162
Max Act: 1.6649. Min Act: -0.1699
Data Index: 8176824 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0162. Min Range: -2.0162
Max Act: 1.6562. Min Act: -0.1700
Data Index: 4298651 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0162. Min Range: -2.0162
Max Act: 1.6649. Min Act: -0.1692
Data Index: 1026512 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0162. Min Range: -2.0162
Max Act: 1.6562. Min Act: -0.1700
Data Index: 4219503 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0162. Min Range: -2.0162
Max Act: 1.6562. Min Act: -0.1700
Data Index: 4917323 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #19