Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3183 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6168. Min Range: -8.6168
Max Act: 8.6168. Min Act: -0.1700
Data Index: 5879844 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6168. Min Range: -8.6168
Max Act: 8.4293. Min Act: -0.1700
Data Index: 3408478 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6168. Min Range: -8.6168
Max Act: 8.3043. Min Act: -0.1700
Data Index: 8282718 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6168. Min Range: -8.6168
Max Act: 8.3043. Min Act: -0.1700
Data Index: 2569478 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6168. Min Range: -8.6168
Max Act: 8.1168. Min Act: -0.1700
Data Index: 8536700 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6168. Min Range: -8.6168
Max Act: 8.1168. Min Act: -0.1700
Data Index: 8000921 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6168. Min Range: -8.6168
Max Act: 7.9918. Min Act: -0.1700
Data Index: 8018017 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6168. Min Range: -8.6168
Max Act: 8.0543. Min Act: -0.1700
Data Index: 423306 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6168. Min Range: -8.6168
Max Act: 7.9293. Min Act: -0.1700
Data Index: 7387771 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6168. Min Range: -8.6168
Max Act: 7.8668. Min Act: -0.1700
Data Index: 3911066 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6168. Min Range: -8.6168
Max Act: 7.8668. Min Act: -0.1700
Data Index: 495660 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6168. Min Range: -8.6168
Max Act: 7.8043. Min Act: -0.1700
Data Index: 4919662 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6168. Min Range: -8.6168
Max Act: 7.8043. Min Act: -0.1700
Data Index: 1278877 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6168. Min Range: -8.6168
Max Act: 7.8043. Min Act: -0.1700
Data Index: 6152536 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6168. Min Range: -8.6168
Max Act: 7.8043. Min Act: -0.1700
Data Index: 71091 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6168. Min Range: -8.6168
Max Act: 7.7418. Min Act: -0.1700
Data Index: 2574815 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6168. Min Range: -8.6168
Max Act: 7.7418. Min Act: -0.1700
Data Index: 2619008 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6168. Min Range: -8.6168
Max Act: 7.7418. Min Act: -0.1700
Data Index: 409369 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6168. Min Range: -8.6168
Max Act: 7.6793. Min Act: -0.1700
Data Index: 1878115 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6168. Min Range: -8.6168
Max Act: 7.6793. Min Act: -0.1700
Data Index: 6230189 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19