Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3023 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2280. Min Range: -5.2280
Max Act: 5.2280. Min Act: -0.1700
Data Index: 8652441 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2280. Min Range: -5.2280
Max Act: 5.1030. Min Act: -0.1700
Data Index: 400692 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2280. Min Range: -5.2280
Max Act: 5.1030. Min Act: -0.1700
Data Index: 4637849 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2280. Min Range: -5.2280
Max Act: 5.0718. Min Act: -0.1700
Data Index: 8017267 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2280. Min Range: -5.2280
Max Act: 5.0718. Min Act: -0.1700
Data Index: 6592025 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2280. Min Range: -5.2280
Max Act: 5.0405. Min Act: -0.1700
Data Index: 5787144 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2280. Min Range: -5.2280
Max Act: 5.0405. Min Act: -0.1700
Data Index: 8247650 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2280. Min Range: -5.2280
Max Act: 5.0405. Min Act: -0.1700
Data Index: 1974230 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2280. Min Range: -5.2280
Max Act: 5.0093. Min Act: -0.1700
Data Index: 2513157 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2280. Min Range: -5.2280
Max Act: 5.0093. Min Act: -0.1700
Data Index: 4019387 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2280. Min Range: -5.2280
Max Act: 5.0093. Min Act: -0.1700
Data Index: 4806189 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2280. Min Range: -5.2280
Max Act: 5.0093. Min Act: -0.1700
Data Index: 5531158 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2280. Min Range: -5.2280
Max Act: 5.0093. Min Act: -0.1700
Data Index: 3263403 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2280. Min Range: -5.2280
Max Act: 4.9780. Min Act: -0.1700
Data Index: 5966917 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2280. Min Range: -5.2280
Max Act: 4.9780. Min Act: -0.1700
Data Index: 5167063 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2280. Min Range: -5.2280
Max Act: 4.9780. Min Act: -0.1700
Data Index: 6090906 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2280. Min Range: -5.2280
Max Act: 4.9780. Min Act: -0.1700
Data Index: 4163090 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2280. Min Range: -5.2280
Max Act: 4.9780. Min Act: -0.1700
Data Index: 4515324 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2280. Min Range: -5.2280
Max Act: 5.0093. Min Act: -0.1700
Data Index: 1909243 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2280. Min Range: -5.2280
Max Act: 4.9780. Min Act: -0.1700
Data Index: 4396680 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #19