Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4780 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7731. Min Range: -5.7731
Max Act: 5.7731. Min Act: -0.1700
Data Index: 6029831 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7731. Min Range: -5.7731
Max Act: 5.5856. Min Act: -0.1700
Data Index: 1653548 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7731. Min Range: -5.7731
Max Act: 5.6169. Min Act: -0.1700
Data Index: 807303 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7731. Min Range: -5.7731
Max Act: 5.5544. Min Act: -0.1700
Data Index: 5020151 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7731. Min Range: -5.7731
Max Act: 5.5544. Min Act: -0.1700
Data Index: 6713242 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7731. Min Range: -5.7731
Max Act: 5.5231. Min Act: -0.1700
Data Index: 2215894 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7731. Min Range: -5.7731
Max Act: 5.5231. Min Act: -0.1700
Data Index: 8214968 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7731. Min Range: -5.7731
Max Act: 5.4919. Min Act: -0.1700
Data Index: 230090 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7731. Min Range: -5.7731
Max Act: 5.4606. Min Act: -0.1700
Data Index: 8024901 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7731. Min Range: -5.7731
Max Act: 5.4606. Min Act: -0.1700
Data Index: 3869811 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7731. Min Range: -5.7731
Max Act: 5.4919. Min Act: -0.1700
Data Index: 7385071 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7731. Min Range: -5.7731
Max Act: 5.4606. Min Act: -0.1700
Data Index: 7293805 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7731. Min Range: -5.7731
Max Act: 5.4294. Min Act: -0.1700
Data Index: 3454329 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7731. Min Range: -5.7731
Max Act: 5.3981. Min Act: -0.1700
Data Index: 1843503 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7731. Min Range: -5.7731
Max Act: 5.4294. Min Act: -0.1700
Data Index: 498095 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7731. Min Range: -5.7731
Max Act: 5.4294. Min Act: -0.1700
Data Index: 5394312 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7731. Min Range: -5.7731
Max Act: 5.3981. Min Act: -0.1700
Data Index: 5904739 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7731. Min Range: -5.7731
Max Act: 5.3981. Min Act: -0.1700
Data Index: 1139019 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7731. Min Range: -5.7731
Max Act: 5.4294. Min Act: -0.1700
Data Index: 394981 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7731. Min Range: -5.7731
Max Act: 5.3981. Min Act: -0.1700
Data Index: 33716 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #19