Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2965 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8883. Min Range: -4.8883
Max Act: 4.8883. Min Act: -0.1700
Data Index: 6650686 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8883. Min Range: -4.8883
Max Act: 4.8571. Min Act: -0.1700
Data Index: 6550627 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8883. Min Range: -4.8883
Max Act: 4.7633. Min Act: -0.1700
Data Index: 8246136 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8883. Min Range: -4.8883
Max Act: 4.7633. Min Act: -0.1700
Data Index: 8450202 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8883. Min Range: -4.8883
Max Act: 4.7633. Min Act: -0.1700
Data Index: 374518 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8883. Min Range: -4.8883
Max Act: 4.7008. Min Act: -0.1700
Data Index: 2171047 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8883. Min Range: -4.8883
Max Act: 4.7321. Min Act: -0.1700
Data Index: 6650690 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8883. Min Range: -4.8883
Max Act: 4.6696. Min Act: -0.1700
Data Index: 2244598 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8883. Min Range: -4.8883
Max Act: 4.7008. Min Act: -0.1700
Data Index: 3329250 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8883. Min Range: -4.8883
Max Act: 4.7008. Min Act: -0.1700
Data Index: 140951 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8883. Min Range: -4.8883
Max Act: 4.7008. Min Act: -0.1700
Data Index: 8163392 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8883. Min Range: -4.8883
Max Act: 4.7008. Min Act: -0.1700
Data Index: 7360071 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8883. Min Range: -4.8883
Max Act: 4.7008. Min Act: -0.1700
Data Index: 566080 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8883. Min Range: -4.8883
Max Act: 4.7008. Min Act: -0.1700
Data Index: 415957 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8883. Min Range: -4.8883
Max Act: 4.6696. Min Act: -0.1700
Data Index: 2854520 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8883. Min Range: -4.8883
Max Act: 4.6696. Min Act: -0.1700
Data Index: 4662703 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8883. Min Range: -4.8883
Max Act: 4.7008. Min Act: -0.1700
Data Index: 3675738 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8883. Min Range: -4.8883
Max Act: 4.6696. Min Act: -0.1700
Data Index: 566086 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8883. Min Range: -4.8883
Max Act: 4.6696. Min Act: -0.1700
Data Index: 1484088 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8883. Min Range: -4.8883
Max Act: 4.6696. Min Act: -0.1700
Data Index: 2500264 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #19