Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3096 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8125. Min Range: -4.8125
Max Act: 4.8125. Min Act: -0.1700
Data Index: 4227777 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8125. Min Range: -4.8125
Max Act: 4.4062. Min Act: -0.1700
Data Index: 7958463 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8125. Min Range: -4.8125
Max Act: 4.4062. Min Act: -0.1700
Data Index: 4133052 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8125. Min Range: -4.8125
Max Act: 4.4375. Min Act: -0.1700
Data Index: 7185251 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8125. Min Range: -4.8125
Max Act: 4.3437. Min Act: -0.1700
Data Index: 5472151 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8125. Min Range: -4.8125
Max Act: 4.2500. Min Act: -0.1700
Data Index: 6493228 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8125. Min Range: -4.8125
Max Act: 4.2187. Min Act: -0.1700
Data Index: 7180516 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8125. Min Range: -4.8125
Max Act: 4.2500. Min Act: -0.1700
Data Index: 3533493 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8125. Min Range: -4.8125
Max Act: 4.2812. Min Act: -0.1700
Data Index: 6343706 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8125. Min Range: -4.8125
Max Act: 4.2187. Min Act: -0.1700
Data Index: 152004 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8125. Min Range: -4.8125
Max Act: 4.2500. Min Act: -0.1700
Data Index: 4507604 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8125. Min Range: -4.8125
Max Act: 4.2187. Min Act: -0.1700
Data Index: 4701477 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8125. Min Range: -4.8125
Max Act: 4.2187. Min Act: -0.1700
Data Index: 6120095 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8125. Min Range: -4.8125
Max Act: 4.1875. Min Act: -0.1700
Data Index: 1355189 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8125. Min Range: -4.8125
Max Act: 4.2187. Min Act: -0.1700
Data Index: 8557106 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8125. Min Range: -4.8125
Max Act: 4.2500. Min Act: -0.1700
Data Index: 6677650 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8125. Min Range: -4.8125
Max Act: 4.1875. Min Act: -0.1700
Data Index: 1245356 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8125. Min Range: -4.8125
Max Act: 4.1875. Min Act: -0.1699
Data Index: 2919216 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8125. Min Range: -4.8125
Max Act: 4.1562. Min Act: -0.1700
Data Index: 3716537 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8125. Min Range: -4.8125
Max Act: 4.1249. Min Act: -0.1700
Data Index: 2753326 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #19