Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3055 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6677. Min Range: -6.6677
Max Act: 6.6364. Min Act: -0.1700
Data Index: 419943 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6677. Min Range: -6.6677
Max Act: 6.5427. Min Act: -0.1700
Data Index: 1179876 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6677. Min Range: -6.6677
Max Act: 6.6677. Min Act: -0.1700
Data Index: 105982 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6677. Min Range: -6.6677
Max Act: 6.5427. Min Act: -0.1700
Data Index: 2255084 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6677. Min Range: -6.6677
Max Act: 6.4177. Min Act: -0.1700
Data Index: 7899861 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6677. Min Range: -6.6677
Max Act: 6.3552. Min Act: -0.1700
Data Index: 4888063 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6677. Min Range: -6.6677
Max Act: 6.2614. Min Act: -0.1700
Data Index: 6544858 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6677. Min Range: -6.6677
Max Act: 6.2614. Min Act: -0.1700
Data Index: 3354998 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6677. Min Range: -6.6677
Max Act: 6.2614. Min Act: -0.1700
Data Index: 8122241 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6677. Min Range: -6.6677
Max Act: 6.1989. Min Act: -0.1700
Data Index: 5634659 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6677. Min Range: -6.6677
Max Act: 6.1677. Min Act: -0.1700
Data Index: 7230759 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6677. Min Range: -6.6677
Max Act: 6.1677. Min Act: -0.1700
Data Index: 5135124 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6677. Min Range: -6.6677
Max Act: 6.1052. Min Act: -0.1700
Data Index: 7149215 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6677. Min Range: -6.6677
Max Act: 6.0739. Min Act: -0.1700
Data Index: 1438363 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6677. Min Range: -6.6677
Max Act: 6.0114. Min Act: -0.1700
Data Index: 5891858 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6677. Min Range: -6.6677
Max Act: 6.0427. Min Act: -0.1700
Data Index: 8231450 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6677. Min Range: -6.6677
Max Act: 6.0114. Min Act: -0.1700
Data Index: 6183133 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6677. Min Range: -6.6677
Max Act: 5.9802. Min Act: -0.1700
Data Index: 561518 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6677. Min Range: -6.6677
Max Act: 6.0114. Min Act: -0.1700
Data Index: 6779821 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6677. Min Range: -6.6677
Max Act: 5.9802. Min Act: -0.1700
Data Index: 3147290 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #19