Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2774 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4373. Min Range: -7.4373
Max Act: 7.4373. Min Act: -0.1700
Data Index: 8703546 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4373. Min Range: -7.4373
Max Act: 7.2498. Min Act: -0.1700
Data Index: 55008 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4373. Min Range: -7.4373
Max Act: 7.2185. Min Act: -0.1700
Data Index: 3229125 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4373. Min Range: -7.4373
Max Act: 7.1248. Min Act: -0.1700
Data Index: 3577292 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4373. Min Range: -7.4373
Max Act: 6.8748. Min Act: -0.1700
Data Index: 8497821 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4373. Min Range: -7.4373
Max Act: 6.8123. Min Act: -0.1700
Data Index: 5745053 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4373. Min Range: -7.4373
Max Act: 6.7810. Min Act: -0.1700
Data Index: 2353555 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4373. Min Range: -7.4373
Max Act: 6.6560. Min Act: -0.1700
Data Index: 5016042 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4373. Min Range: -7.4373
Max Act: 6.6560. Min Act: -0.1700
Data Index: 3188195 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4373. Min Range: -7.4373
Max Act: 6.6873. Min Act: -0.1700
Data Index: 1798814 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4373. Min Range: -7.4373
Max Act: 6.6560. Min Act: -0.1700
Data Index: 8631763 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4373. Min Range: -7.4373
Max Act: 6.6248. Min Act: -0.1700
Data Index: 3038011 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4373. Min Range: -7.4373
Max Act: 6.5935. Min Act: -0.1700
Data Index: 3823490 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4373. Min Range: -7.4373
Max Act: 6.6248. Min Act: -0.1700
Data Index: 4105451 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4373. Min Range: -7.4373
Max Act: 6.6248. Min Act: -0.1700
Data Index: 7613680 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4373. Min Range: -7.4373
Max Act: 6.5935. Min Act: -0.1700
Data Index: 4781430 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4373. Min Range: -7.4373
Max Act: 6.5623. Min Act: -0.1700
Data Index: 4391832 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4373. Min Range: -7.4373
Max Act: 6.5310. Min Act: -0.1700
Data Index: 5521161 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4373. Min Range: -7.4373
Max Act: 6.5623. Min Act: -0.1700
Data Index: 211496 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4373. Min Range: -7.4373
Max Act: 6.5310. Min Act: -0.1700
Data Index: 1758342 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #19