Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 612 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6544. Min Range: -5.6544
Max Act: 5.6544. Min Act: -0.1700
Data Index: 5361839 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6544. Min Range: -5.6544
Max Act: 5.5919. Min Act: -0.1700
Data Index: 2458240 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6544. Min Range: -5.6544
Max Act: 5.5606. Min Act: -0.1700
Data Index: 6218305 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6544. Min Range: -5.6544
Max Act: 5.4981. Min Act: -0.1700
Data Index: 5223755 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6544. Min Range: -5.6544
Max Act: 5.4669. Min Act: -0.1700
Data Index: 3974240 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6544. Min Range: -5.6544
Max Act: 5.4669. Min Act: -0.1700
Data Index: 936748 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6544. Min Range: -5.6544
Max Act: 5.4356. Min Act: -0.1700
Data Index: 4651088 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6544. Min Range: -5.6544
Max Act: 5.4356. Min Act: -0.1700
Data Index: 3145543 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6544. Min Range: -5.6544
Max Act: 5.4044. Min Act: -0.1700
Data Index: 3296568 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6544. Min Range: -5.6544
Max Act: 5.4356. Min Act: -0.1700
Data Index: 4416639 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6544. Min Range: -5.6544
Max Act: 5.4356. Min Act: -0.1700
Data Index: 5451802 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6544. Min Range: -5.6544
Max Act: 5.4356. Min Act: -0.1700
Data Index: 8536180 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6544. Min Range: -5.6544
Max Act: 5.4356. Min Act: -0.1700
Data Index: 8701776 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6544. Min Range: -5.6544
Max Act: 5.4044. Min Act: -0.1700
Data Index: 1161450 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6544. Min Range: -5.6544
Max Act: 5.4044. Min Act: -0.1700
Data Index: 8480939 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6544. Min Range: -5.6544
Max Act: 5.3731. Min Act: -0.1700
Data Index: 1079194 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6544. Min Range: -5.6544
Max Act: 5.3419. Min Act: -0.1700
Data Index: 5496192 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6544. Min Range: -5.6544
Max Act: 5.3419. Min Act: -0.1700
Data Index: 7449946 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6544. Min Range: -5.6544
Max Act: 5.3106. Min Act: -0.1700
Data Index: 1141917 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6544. Min Range: -5.6544
Max Act: 5.3106. Min Act: -0.1700
Data Index: 2333702 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #19