Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 222 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4338. Min Range: -5.4338
Max Act: 5.4338. Min Act: -0.1700
Data Index: 234440 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4338. Min Range: -5.4338
Max Act: 5.4338. Min Act: -0.1700
Data Index: 588908 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4338. Min Range: -5.4338
Max Act: 5.3713. Min Act: -0.1700
Data Index: 4221126 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4338. Min Range: -5.4338
Max Act: 5.3088. Min Act: -0.1700
Data Index: 995524 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4338. Min Range: -5.4338
Max Act: 5.2151. Min Act: -0.1700
Data Index: 54394 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4338. Min Range: -5.4338
Max Act: 5.2463. Min Act: -0.1700
Data Index: 5305221 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4338. Min Range: -5.4338
Max Act: 5.2151. Min Act: -0.1700
Data Index: 7588640 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4338. Min Range: -5.4338
Max Act: 5.2463. Min Act: -0.1700
Data Index: 8629627 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4338. Min Range: -5.4338
Max Act: 5.1838. Min Act: -0.1700
Data Index: 5643547 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4338. Min Range: -5.4338
Max Act: 5.2151. Min Act: -0.1700
Data Index: 6470385 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4338. Min Range: -5.4338
Max Act: 5.2151. Min Act: -0.1700
Data Index: 5724007 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4338. Min Range: -5.4338
Max Act: 5.1526. Min Act: -0.1700
Data Index: 4906102 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4338. Min Range: -5.4338
Max Act: 5.1526. Min Act: -0.1700
Data Index: 1429418 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4338. Min Range: -5.4338
Max Act: 5.0901. Min Act: -0.1700
Data Index: 7924148 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4338. Min Range: -5.4338
Max Act: 5.0901. Min Act: -0.1700
Data Index: 8733601 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4338. Min Range: -5.4338
Max Act: 5.0901. Min Act: -0.1700
Data Index: 833697 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4338. Min Range: -5.4338
Max Act: 5.0901. Min Act: -0.1700
Data Index: 2365683 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4338. Min Range: -5.4338
Max Act: 5.0588. Min Act: -0.1700
Data Index: 7201437 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4338. Min Range: -5.4338
Max Act: 5.0276. Min Act: -0.1700
Data Index: 5604271 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4338. Min Range: -5.4338
Max Act: 5.0276. Min Act: -0.1700
Data Index: 3964773 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #19