Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2655 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5049. Min Range: -6.5049
Max Act: 6.5049. Min Act: -0.1700
Data Index: 2070832 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5049. Min Range: -6.5049
Max Act: 6.3174. Min Act: -0.1700
Data Index: 1099811 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5049. Min Range: -6.5049
Max Act: 6.2862. Min Act: -0.1700
Data Index: 6815020 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5049. Min Range: -6.5049
Max Act: 6.0987. Min Act: -0.1700
Data Index: 4182485 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5049. Min Range: -6.5049
Max Act: 6.0674. Min Act: -0.1700
Data Index: 8628903 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5049. Min Range: -6.5049
Max Act: 6.0049. Min Act: -0.1700
Data Index: 5679490 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5049. Min Range: -6.5049
Max Act: 5.9737. Min Act: -0.1700
Data Index: 5229104 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5049. Min Range: -6.5049
Max Act: 5.9424. Min Act: -0.1700
Data Index: 1984572 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5049. Min Range: -6.5049
Max Act: 5.9737. Min Act: -0.1700
Data Index: 7128113 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5049. Min Range: -6.5049
Max Act: 5.9737. Min Act: -0.1700
Data Index: 3682177 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5049. Min Range: -6.5049
Max Act: 5.9424. Min Act: -0.1700
Data Index: 4637458 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5049. Min Range: -6.5049
Max Act: 5.9424. Min Act: -0.1700
Data Index: 5805288 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5049. Min Range: -6.5049
Max Act: 5.9112. Min Act: -0.1700
Data Index: 3753237 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5049. Min Range: -6.5049
Max Act: 5.9112. Min Act: -0.1700
Data Index: 2770406 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5049. Min Range: -6.5049
Max Act: 5.8799. Min Act: -0.1700
Data Index: 8717351 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5049. Min Range: -6.5049
Max Act: 5.8799. Min Act: -0.1700
Data Index: 2603828 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5049. Min Range: -6.5049
Max Act: 5.8487. Min Act: -0.1700
Data Index: 1515467 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5049. Min Range: -6.5049
Max Act: 5.8487. Min Act: -0.1700
Data Index: 1386574 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5049. Min Range: -6.5049
Max Act: 5.8487. Min Act: -0.1700
Data Index: 4085970 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5049. Min Range: -6.5049
Max Act: 5.8487. Min Act: -0.1700
Data Index: 1140579 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #19