Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2604 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7595. Min Range: -5.7595
Max Act: 5.7595. Min Act: -0.1700
Data Index: 694893 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7595. Min Range: -5.7595
Max Act: 5.6033. Min Act: -0.1700
Data Index: 8702661 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7595. Min Range: -5.7595
Max Act: 5.4783. Min Act: -0.1700
Data Index: 8702660 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7595. Min Range: -5.7595
Max Act: 5.4158. Min Act: -0.1700
Data Index: 4934758 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7595. Min Range: -5.7595
Max Act: 5.3533. Min Act: -0.1700
Data Index: 3172862 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7595. Min Range: -5.7595
Max Act: 5.2908. Min Act: -0.1700
Data Index: 3172863 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7595. Min Range: -5.7595
Max Act: 5.2908. Min Act: -0.1700
Data Index: 7191643 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7595. Min Range: -5.7595
Max Act: 5.2595. Min Act: -0.1700
Data Index: 516233 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7595. Min Range: -5.7595
Max Act: 5.2908. Min Act: -0.1700
Data Index: 2142016 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7595. Min Range: -5.7595
Max Act: 5.2595. Min Act: -0.1700
Data Index: 7134941 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7595. Min Range: -5.7595
Max Act: 5.2283. Min Act: -0.1700
Data Index: 8366074 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7595. Min Range: -5.7595
Max Act: 5.2283. Min Act: -0.1700
Data Index: 892945 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7595. Min Range: -5.7595
Max Act: 5.2283. Min Act: -0.1700
Data Index: 2318774 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7595. Min Range: -5.7595
Max Act: 5.2283. Min Act: -0.1700
Data Index: 8149355 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7595. Min Range: -5.7595
Max Act: 5.2283. Min Act: -0.1700
Data Index: 2361011 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7595. Min Range: -5.7595
Max Act: 5.1970. Min Act: -0.1700
Data Index: 4730362 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7595. Min Range: -5.7595
Max Act: 5.1970. Min Act: -0.1700
Data Index: 4397176 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7595. Min Range: -5.7595
Max Act: 5.1970. Min Act: -0.1700
Data Index: 4229985 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7595. Min Range: -5.7595
Max Act: 5.1970. Min Act: -0.1700
Data Index: 3396886 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7595. Min Range: -5.7595
Max Act: 5.1970. Min Act: -0.1700
Data Index: 6298909 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #19