Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3055 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0070. Min Range: -6.0070
Max Act: 6.0070. Min Act: -0.1700
Data Index: 7848866 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0070. Min Range: -6.0070
Max Act: 5.9758. Min Act: -0.1700
Data Index: 2761089 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0070. Min Range: -6.0070
Max Act: 5.8508. Min Act: -0.1700
Data Index: 4521953 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0070. Min Range: -6.0070
Max Act: 5.7258. Min Act: -0.1700
Data Index: 1788090 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0070. Min Range: -6.0070
Max Act: 5.7258. Min Act: -0.1700
Data Index: 4629946 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0070. Min Range: -6.0070
Max Act: 5.6633. Min Act: -0.1700
Data Index: 6148734 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0070. Min Range: -6.0070
Max Act: 5.6320. Min Act: -0.1700
Data Index: 7467133 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0070. Min Range: -6.0070
Max Act: 5.6320. Min Act: -0.1700
Data Index: 6457875 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0070. Min Range: -6.0070
Max Act: 5.6320. Min Act: -0.1700
Data Index: 1853576 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0070. Min Range: -6.0070
Max Act: 5.6320. Min Act: -0.1700
Data Index: 6871763 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0070. Min Range: -6.0070
Max Act: 5.6008. Min Act: -0.1700
Data Index: 8196622 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0070. Min Range: -6.0070
Max Act: 5.6008. Min Act: -0.1700
Data Index: 86567 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0070. Min Range: -6.0070
Max Act: 5.6008. Min Act: -0.1700
Data Index: 1604118 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0070. Min Range: -6.0070
Max Act: 5.5695. Min Act: -0.1700
Data Index: 3853087 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0070. Min Range: -6.0070
Max Act: 5.5070. Min Act: -0.1700
Data Index: 7332984 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0070. Min Range: -6.0070
Max Act: 5.5383. Min Act: -0.1700
Data Index: 3606675 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0070. Min Range: -6.0070
Max Act: 5.5383. Min Act: -0.1700
Data Index: 938374 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0070. Min Range: -6.0070
Max Act: 5.5383. Min Act: -0.1700
Data Index: 749265 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0070. Min Range: -6.0070
Max Act: 5.5695. Min Act: -0.1700
Data Index: 929906 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0070. Min Range: -6.0070
Max Act: 5.5383. Min Act: -0.1700
Data Index: 6743845 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #19