Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3222 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2528. Min Range: -8.2528
Max Act: 8.2528. Min Act: -0.1700
Data Index: 5823193 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2528. Min Range: -8.2528
Max Act: 8.1278. Min Act: -0.1700
Data Index: 3375112 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2528. Min Range: -8.2528
Max Act: 8.0028. Min Act: -0.1700
Data Index: 2570133 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2528. Min Range: -8.2528
Max Act: 7.8153. Min Act: -0.1700
Data Index: 3338600 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2528. Min Range: -8.2528
Max Act: 7.8153. Min Act: -0.1700
Data Index: 2933414 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2528. Min Range: -8.2528
Max Act: 7.6903. Min Act: -0.1700
Data Index: 5310858 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2528. Min Range: -8.2528
Max Act: 7.6903. Min Act: -0.1700
Data Index: 7728492 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2528. Min Range: -8.2528
Max Act: 7.5653. Min Act: -0.1700
Data Index: 136154 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2528. Min Range: -8.2528
Max Act: 7.6278. Min Act: -0.1700
Data Index: 3348313 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2528. Min Range: -8.2528
Max Act: 7.6278. Min Act: -0.1700
Data Index: 5672368 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2528. Min Range: -8.2528
Max Act: 7.6278. Min Act: -0.1700
Data Index: 23482 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2528. Min Range: -8.2528
Max Act: 7.6278. Min Act: -0.1700
Data Index: 6981691 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2528. Min Range: -8.2528
Max Act: 7.5653. Min Act: -0.1700
Data Index: 6799733 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2528. Min Range: -8.2528
Max Act: 7.5028. Min Act: -0.1700
Data Index: 6167383 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2528. Min Range: -8.2528
Max Act: 7.5653. Min Act: -0.1700
Data Index: 1110690 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2528. Min Range: -8.2528
Max Act: 7.5028. Min Act: -0.1700
Data Index: 7811129 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2528. Min Range: -8.2528
Max Act: 7.4403. Min Act: -0.1698
Data Index: 2082816 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2528. Min Range: -8.2528
Max Act: 7.4403. Min Act: -0.1695
Data Index: 1355109 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2528. Min Range: -8.2528
Max Act: 7.5028. Min Act: -0.1699
Data Index: 7279433 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2528. Min Range: -8.2528
Max Act: 7.5028. Min Act: -0.1700
Data Index: 6564172 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #19