Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 911 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1995. Min Range: -5.1995
Max Act: 5.1995. Min Act: -0.1700
Data Index: 763494 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1995. Min Range: -5.1995
Max Act: 5.1370. Min Act: -0.1700
Data Index: 8213629 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1995. Min Range: -5.1995
Max Act: 5.1057. Min Act: -0.1700
Data Index: 1110316 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1995. Min Range: -5.1995
Max Act: 5.0745. Min Act: -0.1699
Data Index: 2463750 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1995. Min Range: -5.1995
Max Act: 5.0432. Min Act: -0.1698
Data Index: 7153361 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1995. Min Range: -5.1995
Max Act: 5.0120. Min Act: -0.1700
Data Index: 3982289 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1995. Min Range: -5.1995
Max Act: 5.0120. Min Act: -0.1699
Data Index: 1989240 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1995. Min Range: -5.1995
Max Act: 4.9807. Min Act: -0.1700
Data Index: 5630645 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1995. Min Range: -5.1995
Max Act: 4.9807. Min Act: -0.1699
Data Index: 8820528 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1995. Min Range: -5.1995
Max Act: 4.9495. Min Act: -0.1700
Data Index: 2363750 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1995. Min Range: -5.1995
Max Act: 4.9807. Min Act: -0.1700
Data Index: 6761220 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1995. Min Range: -5.1995
Max Act: 4.9495. Min Act: -0.1700
Data Index: 5780033 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1995. Min Range: -5.1995
Max Act: 4.9807. Min Act: -0.1699
Data Index: 94144 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1995. Min Range: -5.1995
Max Act: 5.0120. Min Act: -0.1700
Data Index: 5310360 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1995. Min Range: -5.1995
Max Act: 5.0120. Min Act: -0.1700
Data Index: 5101830 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1995. Min Range: -5.1995
Max Act: 4.9495. Min Act: -0.1696
Data Index: 5036077 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1995. Min Range: -5.1995
Max Act: 4.9807. Min Act: -0.1700
Data Index: 4747479 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1995. Min Range: -5.1995
Max Act: 4.9807. Min Act: -0.1700
Data Index: 1922057 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1995. Min Range: -5.1995
Max Act: 4.9807. Min Act: -0.1699
Data Index: 7379305 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1995. Min Range: -5.1995
Max Act: 4.9807. Min Act: -0.1700
Data Index: 3890415 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19