Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6199 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3307. Min Range: -5.3307
Max Act: 5.3307. Min Act: -0.1700
Data Index: 7694006 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3307. Min Range: -5.3307
Max Act: 5.2057. Min Act: -0.1700
Data Index: 4489183 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3307. Min Range: -5.3307
Max Act: 5.2370. Min Act: -0.1700
Data Index: 5447040 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3307. Min Range: -5.3307
Max Act: 5.2057. Min Act: -0.1700
Data Index: 1575157 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3307. Min Range: -5.3307
Max Act: 5.1745. Min Act: -0.1700
Data Index: 3347372 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3307. Min Range: -5.3307
Max Act: 5.1120. Min Act: -0.1700
Data Index: 227931 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3307. Min Range: -5.3307
Max Act: 5.1120. Min Act: -0.1700
Data Index: 2977536 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3307. Min Range: -5.3307
Max Act: 5.0807. Min Act: -0.1700
Data Index: 910483 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3307. Min Range: -5.3307
Max Act: 5.0807. Min Act: -0.1700
Data Index: 5200516 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3307. Min Range: -5.3307
Max Act: 5.0807. Min Act: -0.1700
Data Index: 4797617 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3307. Min Range: -5.3307
Max Act: 5.0495. Min Act: -0.1700
Data Index: 3029693 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3307. Min Range: -5.3307
Max Act: 5.0495. Min Act: -0.1700
Data Index: 8339815 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3307. Min Range: -5.3307
Max Act: 5.0495. Min Act: -0.1700
Data Index: 8285172 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3307. Min Range: -5.3307
Max Act: 5.0495. Min Act: -0.1700
Data Index: 3370091 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3307. Min Range: -5.3307
Max Act: 5.0495. Min Act: -0.1700
Data Index: 3028595 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3307. Min Range: -5.3307
Max Act: 5.0495. Min Act: -0.1700
Data Index: 8059240 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3307. Min Range: -5.3307
Max Act: 5.0182. Min Act: -0.1700
Data Index: 5369409 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3307. Min Range: -5.3307
Max Act: 5.0495. Min Act: -0.1700
Data Index: 2886870 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3307. Min Range: -5.3307
Max Act: 5.0182. Min Act: -0.1700
Data Index: 2054929 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3307. Min Range: -5.3307
Max Act: 5.0182. Min Act: -0.1700
Data Index: 4393493 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #19