Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1037 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.7592. Min Range: -2.7592
Max Act: 2.7592. Min Act: -0.1700
Data Index: 3236028 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7592. Min Range: -2.7592
Max Act: 2.7432. Min Act: -0.1700
Data Index: 7503789 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7592. Min Range: -2.7592
Max Act: 2.7592. Min Act: -0.1700
Data Index: 5196419 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7592. Min Range: -2.7592
Max Act: 2.7113. Min Act: -0.1700
Data Index: 1127552 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7592. Min Range: -2.7592
Max Act: 2.6953. Min Act: -0.1700
Data Index: 3741710 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7592. Min Range: -2.7592
Max Act: 2.6953. Min Act: -0.1700
Data Index: 2048446 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7592. Min Range: -2.7592
Max Act: 2.6793. Min Act: -0.1700
Data Index: 945638 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7592. Min Range: -2.7592
Max Act: 2.6793. Min Act: -0.1700
Data Index: 7793788 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7592. Min Range: -2.7592
Max Act: 2.6632. Min Act: -0.1700
Data Index: 6138123 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7592. Min Range: -2.7592
Max Act: 2.6632. Min Act: -0.1700
Data Index: 7338349 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7592. Min Range: -2.7592
Max Act: 2.6632. Min Act: -0.1700
Data Index: 4394069 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7592. Min Range: -2.7592
Max Act: 2.6472. Min Act: -0.1700
Data Index: 1761204 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7592. Min Range: -2.7592
Max Act: 2.6472. Min Act: -0.1700
Data Index: 8596159 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7592. Min Range: -2.7592
Max Act: 2.6472. Min Act: -0.1700
Data Index: 2202185 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7592. Min Range: -2.7592
Max Act: 2.6472. Min Act: -0.1700
Data Index: 7843361 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7592. Min Range: -2.7592
Max Act: 2.6311. Min Act: -0.1700
Data Index: 6830614 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7592. Min Range: -2.7592
Max Act: 2.6311. Min Act: -0.1700
Data Index: 908012 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7592. Min Range: -2.7592
Max Act: 2.6151. Min Act: -0.1700
Data Index: 7634058 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7592. Min Range: -2.7592
Max Act: 2.5990. Min Act: -0.1700
Data Index: 3142953 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7592. Min Range: -2.7592
Max Act: 2.6151. Min Act: -0.1700
Data Index: 2259998 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #19