Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1841 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.3235. Min Range: -2.3235
Max Act: 2.3235. Min Act: -0.1700
Data Index: 7624594 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3235. Min Range: -2.3235
Max Act: 2.3071. Min Act: -0.1700
Data Index: 7280969 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3235. Min Range: -2.3235
Max Act: 2.3071. Min Act: -0.1700
Data Index: 988203 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3235. Min Range: -2.3235
Max Act: 2.3071. Min Act: -0.1700
Data Index: 8822723 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3235. Min Range: -2.3235
Max Act: 2.2906. Min Act: -0.1700
Data Index: 3417949 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3235. Min Range: -2.3235
Max Act: 2.2906. Min Act: -0.1700
Data Index: 7282760 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3235. Min Range: -2.3235
Max Act: 2.3071. Min Act: -0.1700
Data Index: 4589686 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3235. Min Range: -2.3235
Max Act: 2.3071. Min Act: -0.1700
Data Index: 8383647 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3235. Min Range: -2.3235
Max Act: 2.2906. Min Act: -0.1700
Data Index: 4045601 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3235. Min Range: -2.3235
Max Act: 2.2742. Min Act: -0.1700
Data Index: 3490678 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3235. Min Range: -2.3235
Max Act: 2.2906. Min Act: -0.1700
Data Index: 1250995 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3235. Min Range: -2.3235
Max Act: 2.2742. Min Act: -0.1700
Data Index: 8212731 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3235. Min Range: -2.3235
Max Act: 2.2742. Min Act: -0.1700
Data Index: 3265979 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3235. Min Range: -2.3235
Max Act: 2.2742. Min Act: -0.1700
Data Index: 2951618 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3235. Min Range: -2.3235
Max Act: 2.2577. Min Act: -0.1700
Data Index: 583378 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3235. Min Range: -2.3235
Max Act: 2.2577. Min Act: -0.1700
Data Index: 8282022 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3235. Min Range: -2.3235
Max Act: 2.2577. Min Act: -0.1700
Data Index: 6613041 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3235. Min Range: -2.3235
Max Act: 2.2577. Min Act: -0.1700
Data Index: 7945056 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3235. Min Range: -2.3235
Max Act: 2.2577. Min Act: -0.1700
Data Index: 3667533 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3235. Min Range: -2.3235
Max Act: 2.2411. Min Act: -0.1700
Data Index: 4045619 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #19