Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2454 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2825. Min Range: -6.2825
Max Act: 6.2825. Min Act: -0.1700
Data Index: 2446181 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2825. Min Range: -6.2825
Max Act: 6.1262. Min Act: -0.1700
Data Index: 3028817 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2825. Min Range: -6.2825
Max Act: 6.0637. Min Act: -0.1700
Data Index: 5278946 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2825. Min Range: -6.2825
Max Act: 5.9387. Min Act: -0.1700
Data Index: 2380711 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2825. Min Range: -6.2825
Max Act: 5.9075. Min Act: -0.1700
Data Index: 8345318 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2825. Min Range: -6.2825
Max Act: 5.8762. Min Act: -0.1700
Data Index: 729026 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2825. Min Range: -6.2825
Max Act: 5.8450. Min Act: -0.1700
Data Index: 2155261 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2825. Min Range: -6.2825
Max Act: 5.8137. Min Act: -0.1700
Data Index: 6157849 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2825. Min Range: -6.2825
Max Act: 5.8137. Min Act: -0.1700
Data Index: 5381980 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2825. Min Range: -6.2825
Max Act: 5.7825. Min Act: -0.1700
Data Index: 5616872 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2825. Min Range: -6.2825
Max Act: 5.7825. Min Act: -0.1700
Data Index: 2599274 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2825. Min Range: -6.2825
Max Act: 5.7512. Min Act: -0.1700
Data Index: 8043431 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2825. Min Range: -6.2825
Max Act: 5.7825. Min Act: -0.1700
Data Index: 4764675 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2825. Min Range: -6.2825
Max Act: 5.7825. Min Act: -0.1700
Data Index: 2645669 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2825. Min Range: -6.2825
Max Act: 5.7512. Min Act: -0.1700
Data Index: 6116570 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2825. Min Range: -6.2825
Max Act: 5.7200. Min Act: -0.1700
Data Index: 8733201 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2825. Min Range: -6.2825
Max Act: 5.7512. Min Act: -0.1700
Data Index: 8195481 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2825. Min Range: -6.2825
Max Act: 5.7200. Min Act: -0.1700
Data Index: 6803209 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2825. Min Range: -6.2825
Max Act: 5.6887. Min Act: -0.1700
Data Index: 8167864 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2825. Min Range: -6.2825
Max Act: 5.6887. Min Act: -0.1700
Data Index: 1965442 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #19