Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2143 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.2410. Min Range: -2.2410
Max Act: 2.2410. Min Act: -0.1700
Data Index: 443096 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2410. Min Range: -2.2410
Max Act: 2.2079. Min Act: -0.1700
Data Index: 2618134 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2410. Min Range: -2.2410
Max Act: 2.1913. Min Act: -0.1700
Data Index: 699371 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2410. Min Range: -2.2410
Max Act: 2.2079. Min Act: -0.1700
Data Index: 7757995 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2410. Min Range: -2.2410
Max Act: 2.1913. Min Act: -0.1700
Data Index: 706364 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2410. Min Range: -2.2410
Max Act: 2.1913. Min Act: -0.1700
Data Index: 4455375 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2410. Min Range: -2.2410
Max Act: 2.1913. Min Act: -0.1700
Data Index: 2575039 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2410. Min Range: -2.2410
Max Act: 2.1913. Min Act: -0.1700
Data Index: 5365196 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2410. Min Range: -2.2410
Max Act: 2.1747. Min Act: -0.1700
Data Index: 8034320 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2410. Min Range: -2.2410
Max Act: 2.1747. Min Act: -0.1700
Data Index: 7341295 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2410. Min Range: -2.2410
Max Act: 2.1747. Min Act: -0.1700
Data Index: 3824437 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2410. Min Range: -2.2410
Max Act: 2.1747. Min Act: -0.1700
Data Index: 6353494 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2410. Min Range: -2.2410
Max Act: 2.1747. Min Act: -0.1700
Data Index: 2111645 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2410. Min Range: -2.2410
Max Act: 2.1747. Min Act: -0.1700
Data Index: 6138736 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2410. Min Range: -2.2410
Max Act: 2.1580. Min Act: -0.1700
Data Index: 3403969 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2410. Min Range: -2.2410
Max Act: 2.1414. Min Act: -0.1700
Data Index: 6317078 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2410. Min Range: -2.2410
Max Act: 2.1247. Min Act: -0.1700
Data Index: 3815213 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2410. Min Range: -2.2410
Max Act: 2.1414. Min Act: -0.1700
Data Index: 699372 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2410. Min Range: -2.2410
Max Act: 2.1414. Min Act: -0.1700
Data Index: 5371173 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2410. Min Range: -2.2410
Max Act: 2.1414. Min Act: -0.1700
Data Index: 4284434 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #19