Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4067 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5689. Min Range: -3.5689
Max Act: 3.5689. Min Act: -0.1700
Data Index: 250275 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5689. Min Range: -3.5689
Max Act: 3.5376. Min Act: -0.1700
Data Index: 2170875 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5689. Min Range: -3.5689
Max Act: 3.5063. Min Act: -0.1700
Data Index: 139180 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5689. Min Range: -3.5689
Max Act: 3.4749. Min Act: -0.1700
Data Index: 3040250 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5689. Min Range: -3.5689
Max Act: 3.5063. Min Act: -0.1700
Data Index: 5662316 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5689. Min Range: -3.5689
Max Act: 3.4436. Min Act: -0.1700
Data Index: 1307362 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5689. Min Range: -3.5689
Max Act: 3.4749. Min Act: -0.1700
Data Index: 2295610 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5689. Min Range: -3.5689
Max Act: 3.4436. Min Act: -0.1700
Data Index: 7474975 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5689. Min Range: -3.5689
Max Act: 3.4436. Min Act: -0.1700
Data Index: 8631867 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5689. Min Range: -3.5689
Max Act: 3.4123. Min Act: -0.1700
Data Index: 487302 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5689. Min Range: -3.5689
Max Act: 3.4123. Min Act: -0.1700
Data Index: 7676486 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5689. Min Range: -3.5689
Max Act: 3.4123. Min Act: -0.1700
Data Index: 6581506 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5689. Min Range: -3.5689
Max Act: 3.4123. Min Act: -0.1700
Data Index: 3197519 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5689. Min Range: -3.5689
Max Act: 3.3809. Min Act: -0.1700
Data Index: 4580673 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5689. Min Range: -3.5689
Max Act: 3.3809. Min Act: -0.1700
Data Index: 8360995 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5689. Min Range: -3.5689
Max Act: 3.3809. Min Act: -0.1700
Data Index: 8252340 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5689. Min Range: -3.5689
Max Act: 3.3809. Min Act: -0.1700
Data Index: 2554394 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5689. Min Range: -3.5689
Max Act: 3.3809. Min Act: -0.1700
Data Index: 7667592 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5689. Min Range: -3.5689
Max Act: 3.3495. Min Act: -0.1700
Data Index: 5812398 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5689. Min Range: -3.5689
Max Act: 3.3495. Min Act: -0.1700
Data Index: 2907148 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19