Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6118 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4059. Min Range: -3.4059
Max Act: 3.3903. Min Act: -0.1700
Data Index: 5810254 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4059. Min Range: -3.4059
Max Act: 3.3903. Min Act: -0.1700
Data Index: 3396352 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4059. Min Range: -3.4059
Max Act: 3.3903. Min Act: -0.1700
Data Index: 2437463 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4059. Min Range: -3.4059
Max Act: 3.4059. Min Act: -0.1700
Data Index: 6468708 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4059. Min Range: -3.4059
Max Act: 3.3275. Min Act: -0.1700
Data Index: 3422073 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4059. Min Range: -3.4059
Max Act: 3.3118. Min Act: -0.1700
Data Index: 4234162 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4059. Min Range: -3.4059
Max Act: 3.3118. Min Act: -0.1700
Data Index: 4087690 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4059. Min Range: -3.4059
Max Act: 3.3118. Min Act: -0.1700
Data Index: 1338550 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4059. Min Range: -3.4059
Max Act: 3.2961. Min Act: -0.1700
Data Index: 7249571 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4059. Min Range: -3.4059
Max Act: 3.2647. Min Act: -0.1700
Data Index: 1644774 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4059. Min Range: -3.4059
Max Act: 3.2647. Min Act: -0.1700
Data Index: 6906888 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4059. Min Range: -3.4059
Max Act: 3.2647. Min Act: -0.1700
Data Index: 3705754 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4059. Min Range: -3.4059
Max Act: 3.2647. Min Act: -0.1700
Data Index: 2297102 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4059. Min Range: -3.4059
Max Act: 3.2490. Min Act: -0.1700
Data Index: 2312484 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4059. Min Range: -3.4059
Max Act: 3.2490. Min Act: -0.1700
Data Index: 8028087 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4059. Min Range: -3.4059
Max Act: 3.2490. Min Act: -0.1700
Data Index: 4357247 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4059. Min Range: -3.4059
Max Act: 3.2490. Min Act: -0.1700
Data Index: 2127550 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4059. Min Range: -3.4059
Max Act: 3.2333. Min Act: -0.1700
Data Index: 3604250 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4059. Min Range: -3.4059
Max Act: 3.2333. Min Act: -0.1700
Data Index: 7183703 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4059. Min Range: -3.4059
Max Act: 3.2333. Min Act: -0.1700
Data Index: 562452 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19