Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3333 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.8054. Min Range: -8.8054
Max Act: 8.8054. Min Act: -0.1700
Data Index: 4552664 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8054. Min Range: -8.8054
Max Act: 8.5554. Min Act: -0.1700
Data Index: 24273 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8054. Min Range: -8.8054
Max Act: 8.4929. Min Act: -0.1700
Data Index: 7784733 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8054. Min Range: -8.8054
Max Act: 8.4929. Min Act: -0.1700
Data Index: 7922367 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8054. Min Range: -8.8054
Max Act: 8.4304. Min Act: -0.1700
Data Index: 2583841 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8054. Min Range: -8.8054
Max Act: 8.4304. Min Act: -0.1700
Data Index: 7784730 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8054. Min Range: -8.8054
Max Act: 8.3054. Min Act: -0.1700
Data Index: 804205 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8054. Min Range: -8.8054
Max Act: 8.3054. Min Act: -0.1700
Data Index: 7784732 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8054. Min Range: -8.8054
Max Act: 8.3679. Min Act: -0.1700
Data Index: 2192832 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8054. Min Range: -8.8054
Max Act: 8.3679. Min Act: -0.1700
Data Index: 7784731 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8054. Min Range: -8.8054
Max Act: 8.3054. Min Act: -0.1700
Data Index: 6171582 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8054. Min Range: -8.8054
Max Act: 8.3054. Min Act: -0.1700
Data Index: 5987795 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8054. Min Range: -8.8054
Max Act: 8.2429. Min Act: -0.1700
Data Index: 5103902 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8054. Min Range: -8.8054
Max Act: 8.2429. Min Act: -0.1700
Data Index: 8477814 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8054. Min Range: -8.8054
Max Act: 8.2429. Min Act: -0.1700
Data Index: 4256769 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8054. Min Range: -8.8054
Max Act: 8.2429. Min Act: -0.1700
Data Index: 2959129 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8054. Min Range: -8.8054
Max Act: 8.1804. Min Act: -0.1700
Data Index: 2807023 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8054. Min Range: -8.8054
Max Act: 8.1804. Min Act: -0.1700
Data Index: 7160075 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8054. Min Range: -8.8054
Max Act: 8.1804. Min Act: -0.1700
Data Index: 5893646 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8054. Min Range: -8.8054
Max Act: 8.1804. Min Act: -0.1700
Data Index: 6167895 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #19