Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2124 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9687. Min Range: -3.9687
Max Act: 3.9687. Min Act: -0.1700
Data Index: 1948072 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9687. Min Range: -3.9687
Max Act: 3.8749. Min Act: -0.1700
Data Index: 2481927 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9687. Min Range: -3.9687
Max Act: 3.8436. Min Act: -0.1700
Data Index: 4976041 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9687. Min Range: -3.9687
Max Act: 3.8436. Min Act: -0.1700
Data Index: 7143628 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9687. Min Range: -3.9687
Max Act: 3.8749. Min Act: -0.1700
Data Index: 833700 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9687. Min Range: -3.9687
Max Act: 3.8436. Min Act: -0.1700
Data Index: 4550798 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9687. Min Range: -3.9687
Max Act: 3.8436. Min Act: -0.1700
Data Index: 6776245 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9687. Min Range: -3.9687
Max Act: 3.8123. Min Act: -0.1700
Data Index: 5922969 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9687. Min Range: -3.9687
Max Act: 3.8123. Min Act: -0.1700
Data Index: 5819858 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9687. Min Range: -3.9687
Max Act: 3.8123. Min Act: -0.1700
Data Index: 6831405 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9687. Min Range: -3.9687
Max Act: 3.8123. Min Act: -0.1700
Data Index: 310865 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9687. Min Range: -3.9687
Max Act: 3.8123. Min Act: -0.1700
Data Index: 6834058 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9687. Min Range: -3.9687
Max Act: 3.8123. Min Act: -0.1700
Data Index: 3073291 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9687. Min Range: -3.9687
Max Act: 3.8436. Min Act: -0.1700
Data Index: 8195940 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9687. Min Range: -3.9687
Max Act: 3.7811. Min Act: -0.1700
Data Index: 8746397 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9687. Min Range: -3.9687
Max Act: 3.7498. Min Act: -0.1700
Data Index: 6434126 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9687. Min Range: -3.9687
Max Act: 3.7498. Min Act: -0.1700
Data Index: 4089445 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9687. Min Range: -3.9687
Max Act: 3.7498. Min Act: -0.1700
Data Index: 6790747 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9687. Min Range: -3.9687
Max Act: 3.7498. Min Act: -0.1700
Data Index: 4524479 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9687. Min Range: -3.9687
Max Act: 3.7498. Min Act: -0.1700
Data Index: 506985 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #19