Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5038 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0567. Min Range: -7.0567
Max Act: 7.0567. Min Act: -0.1700
Data Index: 2017216 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0567. Min Range: -7.0567
Max Act: 6.7755. Min Act: -0.1700
Data Index: 2415289 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0567. Min Range: -7.0567
Max Act: 6.7755. Min Act: -0.1700
Data Index: 2462187 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0567. Min Range: -7.0567
Max Act: 6.8067. Min Act: -0.1700
Data Index: 4781570 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0567. Min Range: -7.0567
Max Act: 6.7130. Min Act: -0.1700
Data Index: 6920298 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0567. Min Range: -7.0567
Max Act: 6.6505. Min Act: -0.1700
Data Index: 7711894 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0567. Min Range: -7.0567
Max Act: 6.6505. Min Act: -0.1700
Data Index: 8414016 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0567. Min Range: -7.0567
Max Act: 6.6192. Min Act: -0.1700
Data Index: 5479329 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0567. Min Range: -7.0567
Max Act: 6.6192. Min Act: -0.1700
Data Index: 143090 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0567. Min Range: -7.0567
Max Act: 6.5880. Min Act: -0.1700
Data Index: 4849253 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0567. Min Range: -7.0567
Max Act: 6.5567. Min Act: -0.1700
Data Index: 4096161 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0567. Min Range: -7.0567
Max Act: 6.5567. Min Act: -0.1700
Data Index: 3563966 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0567. Min Range: -7.0567
Max Act: 6.5880. Min Act: -0.1700
Data Index: 3624203 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0567. Min Range: -7.0567
Max Act: 6.5255. Min Act: -0.1700
Data Index: 7789266 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0567. Min Range: -7.0567
Max Act: 6.4630. Min Act: -0.1700
Data Index: 38195 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0567. Min Range: -7.0567
Max Act: 6.4942. Min Act: -0.1700
Data Index: 7667676 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0567. Min Range: -7.0567
Max Act: 6.4630. Min Act: -0.1700
Data Index: 2575921 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0567. Min Range: -7.0567
Max Act: 6.4630. Min Act: -0.1700
Data Index: 3533036 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0567. Min Range: -7.0567
Max Act: 6.4630. Min Act: -0.1700
Data Index: 5197090 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0567. Min Range: -7.0567
Max Act: 6.4630. Min Act: -0.1700
Data Index: 6989587 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #19