Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1233 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3480. Min Range: -9.3480
Max Act: 9.3480. Min Act: -0.1700
Data Index: 7420756 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3480. Min Range: -9.3480
Max Act: 9.0980. Min Act: -0.1700
Data Index: 5577480 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3480. Min Range: -9.3480
Max Act: 9.1605. Min Act: -0.1700
Data Index: 7821104 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3480. Min Range: -9.3480
Max Act: 9.0980. Min Act: -0.1700
Data Index: 7860499 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3480. Min Range: -9.3480
Max Act: 9.0980. Min Act: -0.1700
Data Index: 3961141 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3480. Min Range: -9.3480
Max Act: 9.0980. Min Act: -0.1700
Data Index: 7869985 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3480. Min Range: -9.3480
Max Act: 8.9730. Min Act: -0.1700
Data Index: 7869998 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3480. Min Range: -9.3480
Max Act: 8.9730. Min Act: -0.1700
Data Index: 1621319 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3480. Min Range: -9.3480
Max Act: 8.9105. Min Act: -0.1700
Data Index: 108191 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3480. Min Range: -9.3480
Max Act: 8.8480. Min Act: -0.1700
Data Index: 6822257 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3480. Min Range: -9.3480
Max Act: 8.7855. Min Act: -0.1700
Data Index: 7266233 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3480. Min Range: -9.3480
Max Act: 8.7855. Min Act: -0.1700
Data Index: 997581 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3480. Min Range: -9.3480
Max Act: 8.7230. Min Act: -0.1700
Data Index: 8234093 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3480. Min Range: -9.3480
Max Act: 8.7230. Min Act: -0.1700
Data Index: 5416178 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3480. Min Range: -9.3480
Max Act: 8.7230. Min Act: -0.1700
Data Index: 4610112 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3480. Min Range: -9.3480
Max Act: 8.7230. Min Act: -0.1700
Data Index: 8627412 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3480. Min Range: -9.3480
Max Act: 8.7230. Min Act: -0.1700
Data Index: 8656148 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3480. Min Range: -9.3480
Max Act: 8.7230. Min Act: -0.1700
Data Index: 1881332 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3480. Min Range: -9.3480
Max Act: 8.7230. Min Act: -0.1700
Data Index: 5739303 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3480. Min Range: -9.3480
Max Act: 8.6605. Min Act: -0.1700
Data Index: 2115203 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #19