Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3580 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4136. Min Range: -5.4136
Max Act: 5.4136. Min Act: -0.1700
Data Index: 340236 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4136. Min Range: -5.4136
Max Act: 5.3824. Min Act: -0.1700
Data Index: 3310531 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4136. Min Range: -5.4136
Max Act: 5.2574. Min Act: -0.1700
Data Index: 7240590 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4136. Min Range: -5.4136
Max Act: 5.2261. Min Act: -0.1700
Data Index: 5830779 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4136. Min Range: -5.4136
Max Act: 5.1949. Min Act: -0.1700
Data Index: 8074277 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4136. Min Range: -5.4136
Max Act: 5.1949. Min Act: -0.1700
Data Index: 3056279 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4136. Min Range: -5.4136
Max Act: 5.1324. Min Act: -0.1700
Data Index: 8671752 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4136. Min Range: -5.4136
Max Act: 5.1324. Min Act: -0.1700
Data Index: 7669977 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4136. Min Range: -5.4136
Max Act: 5.1011. Min Act: -0.1700
Data Index: 2065248 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4136. Min Range: -5.4136
Max Act: 5.1011. Min Act: -0.1700
Data Index: 906811 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4136. Min Range: -5.4136
Max Act: 5.1011. Min Act: -0.1700
Data Index: 2944861 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4136. Min Range: -5.4136
Max Act: 5.0699. Min Act: -0.1700
Data Index: 6284278 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4136. Min Range: -5.4136
Max Act: 5.0699. Min Act: -0.1700
Data Index: 2136406 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4136. Min Range: -5.4136
Max Act: 5.0386. Min Act: -0.1700
Data Index: 3501641 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4136. Min Range: -5.4136
Max Act: 5.0386. Min Act: -0.1700
Data Index: 6719507 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4136. Min Range: -5.4136
Max Act: 5.0386. Min Act: -0.1700
Data Index: 6439955 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4136. Min Range: -5.4136
Max Act: 5.0386. Min Act: -0.1700
Data Index: 2224504 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4136. Min Range: -5.4136
Max Act: 5.0074. Min Act: -0.1700
Data Index: 5083844 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4136. Min Range: -5.4136
Max Act: 5.0074. Min Act: -0.1700
Data Index: 5657522 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4136. Min Range: -5.4136
Max Act: 5.0074. Min Act: -0.1700
Data Index: 8566910 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #19