Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4981 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.4683. Min Range: -1.4683
Max Act: 1.4683. Min Act: -0.1700
Data Index: 8086133 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4683. Min Range: -1.4683
Max Act: 1.4507. Min Act: -0.1700
Data Index: 729896 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4683. Min Range: -1.4683
Max Act: 1.3626. Min Act: -0.1700
Data Index: 7164711 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4683. Min Range: -1.4683
Max Act: 1.3626. Min Act: -0.1700
Data Index: 4724734 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4683. Min Range: -1.4683
Max Act: 1.3273. Min Act: -0.1700
Data Index: 1665394 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4683. Min Range: -1.4683
Max Act: 1.3450. Min Act: -0.1700
Data Index: 8075626 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4683. Min Range: -1.4683
Max Act: 1.3450. Min Act: -0.1700
Data Index: 5138196 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4683. Min Range: -1.4683
Max Act: 1.3097. Min Act: -0.1700
Data Index: 1730225 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4683. Min Range: -1.4683
Max Act: 1.2921. Min Act: -0.1700
Data Index: 6624015 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4683. Min Range: -1.4683
Max Act: 1.3097. Min Act: -0.1700
Data Index: 2886905 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4683. Min Range: -1.4683
Max Act: 1.3097. Min Act: -0.1700
Data Index: 3942203 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4683. Min Range: -1.4683
Max Act: 1.3273. Min Act: -0.1700
Data Index: 408980 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4683. Min Range: -1.4683
Max Act: 1.3097. Min Act: -0.1700
Data Index: 2472071 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4683. Min Range: -1.4683
Max Act: 1.2921. Min Act: -0.1700
Data Index: 3196614 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4683. Min Range: -1.4683
Max Act: 1.2921. Min Act: -0.1700
Data Index: 1622533 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4683. Min Range: -1.4683
Max Act: 1.2921. Min Act: -0.1700
Data Index: 3100046 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4683. Min Range: -1.4683
Max Act: 1.2921. Min Act: -0.1700
Data Index: 1915548 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4683. Min Range: -1.4683
Max Act: 1.2744. Min Act: -0.1700
Data Index: 2831144 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4683. Min Range: -1.4683
Max Act: 1.2921. Min Act: -0.1700
Data Index: 2702829 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4683. Min Range: -1.4683
Max Act: 1.2744. Min Act: -0.1700
Data Index: 358841 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #19