Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5556 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2885. Min Range: -8.2885
Max Act: 8.2885. Min Act: -0.1700
Data Index: 1276978 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2885. Min Range: -8.2885
Max Act: 7.8510. Min Act: -0.1700
Data Index: 6174338 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2885. Min Range: -8.2885
Max Act: 7.7885. Min Act: -0.1697
Data Index: 1721855 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2885. Min Range: -8.2885
Max Act: 7.6948. Min Act: -0.1700
Data Index: 8699776 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2885. Min Range: -8.2885
Max Act: 7.6010. Min Act: -0.1700
Data Index: 7906355 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2885. Min Range: -8.2885
Max Act: 7.5073. Min Act: -0.1700
Data Index: 8672148 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2885. Min Range: -8.2885
Max Act: 7.4760. Min Act: -0.1700
Data Index: 4306034 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2885. Min Range: -8.2885
Max Act: 7.4760. Min Act: -0.1700
Data Index: 1151160 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2885. Min Range: -8.2885
Max Act: 7.5073. Min Act: -0.1700
Data Index: 4067972 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2885. Min Range: -8.2885
Max Act: 7.4760. Min Act: -0.1700
Data Index: 4534731 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2885. Min Range: -8.2885
Max Act: 7.4448. Min Act: -0.1700
Data Index: 8122471 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2885. Min Range: -8.2885
Max Act: 7.4448. Min Act: -0.1700
Data Index: 6845372 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2885. Min Range: -8.2885
Max Act: 7.4135. Min Act: -0.1700
Data Index: 3751252 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2885. Min Range: -8.2885
Max Act: 7.4135. Min Act: -0.1700
Data Index: 8684878 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2885. Min Range: -8.2885
Max Act: 7.4135. Min Act: -0.1700
Data Index: 7078263 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2885. Min Range: -8.2885
Max Act: 7.3823. Min Act: -0.1700
Data Index: 2856702 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2885. Min Range: -8.2885
Max Act: 7.3823. Min Act: -0.1700
Data Index: 3496721 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2885. Min Range: -8.2885
Max Act: 7.3823. Min Act: -0.1700
Data Index: 4688939 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2885. Min Range: -8.2885
Max Act: 7.4135. Min Act: -0.1700
Data Index: 6497247 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2885. Min Range: -8.2885
Max Act: 7.4135. Min Act: -0.1700
Data Index: 7032030 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #19