Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2929 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7091. Min Range: -8.7091
Max Act: 8.7091. Min Act: -0.1700
Data Index: 3552150 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7091. Min Range: -8.7091
Max Act: 8.7091. Min Act: -0.1700
Data Index: 2327923 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7091. Min Range: -8.7091
Max Act: 8.6466. Min Act: -0.1700
Data Index: 8186639 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7091. Min Range: -8.7091
Max Act: 8.4591. Min Act: -0.1700
Data Index: 288140 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7091. Min Range: -8.7091
Max Act: 8.4591. Min Act: -0.1700
Data Index: 2548999 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7091. Min Range: -8.7091
Max Act: 8.3341. Min Act: -0.1700
Data Index: 3579613 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7091. Min Range: -8.7091
Max Act: 8.3341. Min Act: -0.1700
Data Index: 2980019 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7091. Min Range: -8.7091
Max Act: 8.3341. Min Act: -0.1700
Data Index: 1117471 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7091. Min Range: -8.7091
Max Act: 8.3341. Min Act: -0.1700
Data Index: 3972660 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7091. Min Range: -8.7091
Max Act: 8.2716. Min Act: -0.1700
Data Index: 1941020 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7091. Min Range: -8.7091
Max Act: 8.2091. Min Act: -0.1700
Data Index: 3364556 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7091. Min Range: -8.7091
Max Act: 8.1466. Min Act: -0.1700
Data Index: 1609137 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7091. Min Range: -8.7091
Max Act: 8.1466. Min Act: -0.1700
Data Index: 2151118 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7091. Min Range: -8.7091
Max Act: 8.1466. Min Act: -0.1700
Data Index: 8828461 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7091. Min Range: -8.7091
Max Act: 8.1466. Min Act: -0.1700
Data Index: 8216102 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7091. Min Range: -8.7091
Max Act: 8.1466. Min Act: -0.1700
Data Index: 8005493 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7091. Min Range: -8.7091
Max Act: 8.1466. Min Act: -0.1700
Data Index: 242144 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7091. Min Range: -8.7091
Max Act: 8.0841. Min Act: -0.1700
Data Index: 3573102 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7091. Min Range: -8.7091
Max Act: 8.0841. Min Act: -0.1700
Data Index: 4923539 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7091. Min Range: -8.7091
Max Act: 8.0841. Min Act: -0.1700
Data Index: 5386991 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #19