Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3578 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9457. Min Range: -3.9457
Max Act: 3.9457. Min Act: -0.1700
Data Index: 2299520 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9457. Min Range: -3.9457
Max Act: 3.8206. Min Act: -0.1700
Data Index: 3880647 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9457. Min Range: -3.9457
Max Act: 3.7268. Min Act: -0.1700
Data Index: 1821391 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9457. Min Range: -3.9457
Max Act: 3.6642. Min Act: -0.1700
Data Index: 1155106 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9457. Min Range: -3.9457
Max Act: 3.6016. Min Act: -0.1700
Data Index: 594042 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9457. Min Range: -3.9457
Max Act: 3.5703. Min Act: -0.1700
Data Index: 2103591 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9457. Min Range: -3.9457
Max Act: 3.5390. Min Act: -0.1700
Data Index: 1732557 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9457. Min Range: -3.9457
Max Act: 3.4764. Min Act: -0.1700
Data Index: 3880646 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9457. Min Range: -3.9457
Max Act: 3.4450. Min Act: -0.1700
Data Index: 7068636 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9457. Min Range: -3.9457
Max Act: 3.4607. Min Act: -0.1700
Data Index: 5775241 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9457. Min Range: -3.9457
Max Act: 3.4450. Min Act: -0.1700
Data Index: 1155108 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9457. Min Range: -3.9457
Max Act: 3.4450. Min Act: -0.1700
Data Index: 5833533 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9457. Min Range: -3.9457
Max Act: 3.4450. Min Act: -0.1700
Data Index: 530236 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9457. Min Range: -3.9457
Max Act: 3.4607. Min Act: -0.1700
Data Index: 4391627 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9457. Min Range: -3.9457
Max Act: 3.4450. Min Act: -0.1700
Data Index: 3962661 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9457. Min Range: -3.9457
Max Act: 3.4294. Min Act: -0.1700
Data Index: 1801600 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9457. Min Range: -3.9457
Max Act: 3.4294. Min Act: -0.1700
Data Index: 1879314 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9457. Min Range: -3.9457
Max Act: 3.3980. Min Act: -0.1700
Data Index: 6513882 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9457. Min Range: -3.9457
Max Act: 3.4137. Min Act: -0.1700
Data Index: 6879398 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9457. Min Range: -3.9457
Max Act: 3.4137. Min Act: -0.1700
Data Index: 8764700 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #19