Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3005 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1103. Min Range: -8.1103
Max Act: 8.1103. Min Act: -0.1700
Data Index: 8793609 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1103. Min Range: -8.1103
Max Act: 8.0478. Min Act: -0.1700
Data Index: 8036848 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1103. Min Range: -8.1103
Max Act: 7.9853. Min Act: -0.1700
Data Index: 3641593 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1103. Min Range: -8.1103
Max Act: 7.7978. Min Act: -0.1700
Data Index: 935787 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1103. Min Range: -8.1103
Max Act: 7.7978. Min Act: -0.1700
Data Index: 1271819 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1103. Min Range: -8.1103
Max Act: 7.7978. Min Act: -0.1700
Data Index: 128791 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1103. Min Range: -8.1103
Max Act: 7.7041. Min Act: -0.1700
Data Index: 4941287 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1103. Min Range: -8.1103
Max Act: 7.7353. Min Act: -0.1700
Data Index: 3871826 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1103. Min Range: -8.1103
Max Act: 7.7041. Min Act: -0.1700
Data Index: 6783668 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1103. Min Range: -8.1103
Max Act: 7.7041. Min Act: -0.1700
Data Index: 1917134 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1103. Min Range: -8.1103
Max Act: 7.7041. Min Act: -0.1700
Data Index: 2497298 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1103. Min Range: -8.1103
Max Act: 7.6728. Min Act: -0.1700
Data Index: 7363941 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1103. Min Range: -8.1103
Max Act: 7.6728. Min Act: -0.1700
Data Index: 5486429 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1103. Min Range: -8.1103
Max Act: 7.6416. Min Act: -0.1700
Data Index: 7730979 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1103. Min Range: -8.1103
Max Act: 7.6416. Min Act: -0.1700
Data Index: 1917135 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1103. Min Range: -8.1103
Max Act: 7.6416. Min Act: -0.1700
Data Index: 3137682 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1103. Min Range: -8.1103
Max Act: 7.6103. Min Act: -0.1700
Data Index: 5425942 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1103. Min Range: -8.1103
Max Act: 7.6103. Min Act: -0.1700
Data Index: 6481794 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1103. Min Range: -8.1103
Max Act: 7.6103. Min Act: -0.1700
Data Index: 8036845 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1103. Min Range: -8.1103
Max Act: 7.6103. Min Act: -0.1700
Data Index: 4816620 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #19