Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 673 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3645. Min Range: -4.3645
Max Act: 4.3645. Min Act: -0.1700
Data Index: 5706760 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3645. Min Range: -4.3645
Max Act: 4.3645. Min Act: -0.1700
Data Index: 2479554 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3645. Min Range: -4.3645
Max Act: 4.3645. Min Act: -0.1700
Data Index: 5706758 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3645. Min Range: -4.3645
Max Act: 4.3333. Min Act: -0.1700
Data Index: 46205 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3645. Min Range: -4.3645
Max Act: 4.3333. Min Act: -0.1700
Data Index: 627238 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3645. Min Range: -4.3645
Max Act: 4.3333. Min Act: -0.1700
Data Index: 1108659 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3645. Min Range: -4.3645
Max Act: 4.3333. Min Act: -0.1700
Data Index: 1642926 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3645. Min Range: -4.3645
Max Act: 4.3020. Min Act: -0.1700
Data Index: 2122202 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3645. Min Range: -4.3645
Max Act: 4.3020. Min Act: -0.1700
Data Index: 3858336 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3645. Min Range: -4.3645
Max Act: 4.3020. Min Act: -0.1700
Data Index: 3786158 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3645. Min Range: -4.3645
Max Act: 4.3020. Min Act: -0.1700
Data Index: 3695074 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3645. Min Range: -4.3645
Max Act: 4.3020. Min Act: -0.1700
Data Index: 3654538 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3645. Min Range: -4.3645
Max Act: 4.3020. Min Act: -0.1700
Data Index: 4709942 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3645. Min Range: -4.3645
Max Act: 4.3333. Min Act: -0.1700
Data Index: 3618338 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3645. Min Range: -4.3645
Max Act: 4.3020. Min Act: -0.1700
Data Index: 641134 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3645. Min Range: -4.3645
Max Act: 4.3020. Min Act: -0.1700
Data Index: 3954989 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3645. Min Range: -4.3645
Max Act: 4.3020. Min Act: -0.1700
Data Index: 1953643 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3645. Min Range: -4.3645
Max Act: 4.3333. Min Act: -0.1700
Data Index: 1946202 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3645. Min Range: -4.3645
Max Act: 4.3020. Min Act: -0.1700
Data Index: 1643162 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3645. Min Range: -4.3645
Max Act: 4.3020. Min Act: -0.1700
Data Index: 3868091 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19