Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3346 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2070. Min Range: -5.2070
Max Act: 5.2070. Min Act: -0.1700
Data Index: 6385739 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2070. Min Range: -5.2070
Max Act: 5.1445. Min Act: -0.1700
Data Index: 5425478 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2070. Min Range: -5.2070
Max Act: 5.1132. Min Act: -0.1700
Data Index: 2982222 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2070. Min Range: -5.2070
Max Act: 5.1132. Min Act: -0.1700
Data Index: 6626293 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2070. Min Range: -5.2070
Max Act: 5.0820. Min Act: -0.1700
Data Index: 1805382 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2070. Min Range: -5.2070
Max Act: 5.0507. Min Act: -0.1700
Data Index: 7868701 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2070. Min Range: -5.2070
Max Act: 5.0507. Min Act: -0.1700
Data Index: 626319 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2070. Min Range: -5.2070
Max Act: 5.0507. Min Act: -0.1700
Data Index: 6626294 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2070. Min Range: -5.2070
Max Act: 5.0195. Min Act: -0.1700
Data Index: 3475283 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2070. Min Range: -5.2070
Max Act: 4.9882. Min Act: -0.1700
Data Index: 5425476 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2070. Min Range: -5.2070
Max Act: 4.9882. Min Act: -0.1700
Data Index: 1825824 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2070. Min Range: -5.2070
Max Act: 4.9882. Min Act: -0.1700
Data Index: 7335171 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2070. Min Range: -5.2070
Max Act: 4.9882. Min Act: -0.1700
Data Index: 2448642 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2070. Min Range: -5.2070
Max Act: 4.9882. Min Act: -0.1698
Data Index: 3785920 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2070. Min Range: -5.2070
Max Act: 4.9570. Min Act: -0.1700
Data Index: 4345 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2070. Min Range: -5.2070
Max Act: 4.9882. Min Act: -0.1700
Data Index: 3627999 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2070. Min Range: -5.2070
Max Act: 4.9882. Min Act: -0.1700
Data Index: 2184736 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2070. Min Range: -5.2070
Max Act: 4.9882. Min Act: -0.1700
Data Index: 1313111 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2070. Min Range: -5.2070
Max Act: 4.9570. Min Act: -0.1700
Data Index: 7256272 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2070. Min Range: -5.2070
Max Act: 4.9570. Min Act: -0.1700
Data Index: 7573207 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #19