Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3083 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9948. Min Range: -8.9948
Max Act: 8.9948. Min Act: -0.1700
Data Index: 2767230 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9948. Min Range: -8.9948
Max Act: 8.9948. Min Act: -0.1700
Data Index: 1173477 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9948. Min Range: -8.9948
Max Act: 8.9323. Min Act: -0.1700
Data Index: 5838759 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9948. Min Range: -8.9948
Max Act: 8.8698. Min Act: -0.1700
Data Index: 7854040 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9948. Min Range: -8.9948
Max Act: 8.8698. Min Act: -0.1700
Data Index: 7423783 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9948. Min Range: -8.9948
Max Act: 8.8073. Min Act: -0.1700
Data Index: 6484217 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9948. Min Range: -8.9948
Max Act: 8.8698. Min Act: -0.1700
Data Index: 5317357 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9948. Min Range: -8.9948
Max Act: 8.8073. Min Act: -0.1700
Data Index: 4265097 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9948. Min Range: -8.9948
Max Act: 8.7448. Min Act: -0.1700
Data Index: 6834231 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9948. Min Range: -8.9948
Max Act: 8.7448. Min Act: -0.1700
Data Index: 772002 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9948. Min Range: -8.9948
Max Act: 8.8073. Min Act: -0.1700
Data Index: 148080 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9948. Min Range: -8.9948
Max Act: 8.6823. Min Act: -0.1700
Data Index: 8161987 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9948. Min Range: -8.9948
Max Act: 8.5573. Min Act: -0.1700
Data Index: 5978623 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9948. Min Range: -8.9948
Max Act: 8.6198. Min Act: -0.1700
Data Index: 3699615 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9948. Min Range: -8.9948
Max Act: 8.5573. Min Act: -0.1700
Data Index: 4078256 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9948. Min Range: -8.9948
Max Act: 8.4948. Min Act: -0.1700
Data Index: 4821407 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9948. Min Range: -8.9948
Max Act: 8.4323. Min Act: -0.1700
Data Index: 4523003 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9948. Min Range: -8.9948
Max Act: 8.4948. Min Act: -0.1700
Data Index: 2239264 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9948. Min Range: -8.9948
Max Act: 8.4948. Min Act: -0.1700
Data Index: 4062961 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9948. Min Range: -8.9948
Max Act: 8.4948. Min Act: -0.1700
Data Index: 6600315 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #19