Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 2422 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 4.2729. Min Range: -4.2729
Max Act: 4.2729. Min Act: -0.1700
Data Index: 7866509 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2729. Min Range: -4.2729
Max Act: 4.1166. Min Act: -0.1700
Data Index: 2600063 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2729. Min Range: -4.2729
Max Act: 4.1166. Min Act: -0.1700
Data Index: 6137231 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2729. Min Range: -4.2729
Max Act: 4.0854. Min Act: -0.1700
Data Index: 7196757 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2729. Min Range: -4.2729
Max Act: 4.0541. Min Act: -0.1700
Data Index: 4723231 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2729. Min Range: -4.2729
Max Act: 4.0229. Min Act: -0.1700
Data Index: 8645485 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2729. Min Range: -4.2729
Max Act: 4.0541. Min Act: -0.1700
Data Index: 4754710 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2729. Min Range: -4.2729
Max Act: 4.0229. Min Act: -0.1700
Data Index: 3902414 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2729. Min Range: -4.2729
Max Act: 4.0541. Min Act: -0.1700
Data Index: 6169420 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2729. Min Range: -4.2729
Max Act: 4.0229. Min Act: -0.1700
Data Index: 6266072 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2729. Min Range: -4.2729
Max Act: 4.0229. Min Act: -0.1700
Data Index: 7254515 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2729. Min Range: -4.2729
Max Act: 4.0541. Min Act: -0.1700
Data Index: 364300 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2729. Min Range: -4.2729
Max Act: 3.9916. Min Act: -0.1700
Data Index: 1102751 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2729. Min Range: -4.2729
Max Act: 3.9916. Min Act: -0.1700
Data Index: 5778007 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2729. Min Range: -4.2729
Max Act: 3.9916. Min Act: -0.1700
Data Index: 999825 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2729. Min Range: -4.2729
Max Act: 3.9916. Min Act: -0.1700
Data Index: 3518110 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2729. Min Range: -4.2729
Max Act: 3.9916. Min Act: -0.1700
Data Index: 3741321 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2729. Min Range: -4.2729
Max Act: 3.9916. Min Act: -0.1698
Data Index: 574153 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2729. Min Range: -4.2729
Max Act: 3.9916. Min Act: -0.1700
Data Index: 5887676 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2729. Min Range: -4.2729
Max Act: 4.0229. Min Act: -0.1700
Data Index: 3082587 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #19