Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 840 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2487. Min Range: -5.2487
Max Act: 5.2487. Min Act: -0.1699
Data Index: 1293466 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2487. Min Range: -5.2487
Max Act: 5.2174. Min Act: -0.1700
Data Index: 3295814 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2487. Min Range: -5.2487
Max Act: 5.1862. Min Act: -0.1700
Data Index: 6953607 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2487. Min Range: -5.2487
Max Act: 5.1862. Min Act: -0.1700
Data Index: 8184194 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2487. Min Range: -5.2487
Max Act: 5.1237. Min Act: -0.1700
Data Index: 6322692 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2487. Min Range: -5.2487
Max Act: 5.1237. Min Act: -0.1700
Data Index: 8497148 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2487. Min Range: -5.2487
Max Act: 5.0924. Min Act: -0.1700
Data Index: 4303530 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2487. Min Range: -5.2487
Max Act: 5.0924. Min Act: -0.1700
Data Index: 6727020 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2487. Min Range: -5.2487
Max Act: 5.0924. Min Act: -0.1697
Data Index: 4699080 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2487. Min Range: -5.2487
Max Act: 5.0924. Min Act: -0.1700
Data Index: 4318414 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2487. Min Range: -5.2487
Max Act: 5.0924. Min Act: -0.1694
Data Index: 1968451 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2487. Min Range: -5.2487
Max Act: 5.0612. Min Act: -0.1696
Data Index: 3939625 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2487. Min Range: -5.2487
Max Act: 5.0924. Min Act: -0.1698
Data Index: 1749914 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2487. Min Range: -5.2487
Max Act: 5.0924. Min Act: -0.1700
Data Index: 6873650 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2487. Min Range: -5.2487
Max Act: 5.0924. Min Act: -0.1700
Data Index: 2455229 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2487. Min Range: -5.2487
Max Act: 5.0612. Min Act: -0.1700
Data Index: 4195826 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2487. Min Range: -5.2487
Max Act: 5.0612. Min Act: -0.1699
Data Index: 4113538 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2487. Min Range: -5.2487
Max Act: 5.0612. Min Act: -0.1700
Data Index: 4619850 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2487. Min Range: -5.2487
Max Act: 5.0612. Min Act: -0.1700
Data Index: 5013170 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2487. Min Range: -5.2487
Max Act: 5.0299. Min Act: -0.1669
Data Index: 2319921 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #19