Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3494 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3151. Min Range: -5.3151
Max Act: 5.3151. Min Act: -0.1700
Data Index: 3769173 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3151. Min Range: -5.3151
Max Act: 5.3151. Min Act: -0.1700
Data Index: 369026 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3151. Min Range: -5.3151
Max Act: 5.2839. Min Act: -0.1700
Data Index: 7975270 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3151. Min Range: -5.3151
Max Act: 5.2839. Min Act: -0.1700
Data Index: 1544777 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3151. Min Range: -5.3151
Max Act: 5.2526. Min Act: -0.1700
Data Index: 2980908 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3151. Min Range: -5.3151
Max Act: 5.2526. Min Act: -0.1700
Data Index: 7417301 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3151. Min Range: -5.3151
Max Act: 5.2526. Min Act: -0.1700
Data Index: 2200431 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3151. Min Range: -5.3151
Max Act: 5.2214. Min Act: -0.1700
Data Index: 7339618 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3151. Min Range: -5.3151
Max Act: 5.2214. Min Act: -0.1700
Data Index: 1999202 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3151. Min Range: -5.3151
Max Act: 5.1901. Min Act: -0.1700
Data Index: 5444185 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3151. Min Range: -5.3151
Max Act: 5.1901. Min Act: -0.1700
Data Index: 1206906 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3151. Min Range: -5.3151
Max Act: 5.1589. Min Act: -0.1700
Data Index: 3736239 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3151. Min Range: -5.3151
Max Act: 5.1589. Min Act: -0.1700
Data Index: 2780137 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3151. Min Range: -5.3151
Max Act: 5.1589. Min Act: -0.1700
Data Index: 156528 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3151. Min Range: -5.3151
Max Act: 5.1276. Min Act: -0.1700
Data Index: 7601167 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3151. Min Range: -5.3151
Max Act: 5.1276. Min Act: -0.1700
Data Index: 1308290 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3151. Min Range: -5.3151
Max Act: 5.0964. Min Act: -0.1700
Data Index: 940957 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3151. Min Range: -5.3151
Max Act: 5.0964. Min Act: -0.1700
Data Index: 466949 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3151. Min Range: -5.3151
Max Act: 5.0651. Min Act: -0.1700
Data Index: 5676842 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3151. Min Range: -5.3151
Max Act: 5.0964. Min Act: -0.1700
Data Index: 7338123 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #19