Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6074 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4995. Min Range: -6.4995
Max Act: 6.4995. Min Act: -0.1700
Data Index: 467768 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4995. Min Range: -6.4995
Max Act: 6.3433. Min Act: -0.1700
Data Index: 3060301 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4995. Min Range: -6.4995
Max Act: 6.2808. Min Act: -0.1700
Data Index: 3929765 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4995. Min Range: -6.4995
Max Act: 6.1558. Min Act: -0.1700
Data Index: 6352805 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4995. Min Range: -6.4995
Max Act: 6.1245. Min Act: -0.1700
Data Index: 1654299 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4995. Min Range: -6.4995
Max Act: 6.0933. Min Act: -0.1700
Data Index: 3260504 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4995. Min Range: -6.4995
Max Act: 6.0933. Min Act: -0.1700
Data Index: 4128895 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4995. Min Range: -6.4995
Max Act: 6.0620. Min Act: -0.1700
Data Index: 8304151 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4995. Min Range: -6.4995
Max Act: 6.0620. Min Act: -0.1700
Data Index: 296617 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4995. Min Range: -6.4995
Max Act: 6.0620. Min Act: -0.1700
Data Index: 4925501 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4995. Min Range: -6.4995
Max Act: 5.9683. Min Act: -0.1700
Data Index: 6652187 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4995. Min Range: -6.4995
Max Act: 5.9683. Min Act: -0.1700
Data Index: 7362700 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4995. Min Range: -6.4995
Max Act: 5.9370. Min Act: -0.1700
Data Index: 8411180 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4995. Min Range: -6.4995
Max Act: 5.9370. Min Act: -0.1700
Data Index: 6863157 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4995. Min Range: -6.4995
Max Act: 5.9058. Min Act: -0.1700
Data Index: 6712437 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4995. Min Range: -6.4995
Max Act: 5.9058. Min Act: -0.1700
Data Index: 264829 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4995. Min Range: -6.4995
Max Act: 5.9058. Min Act: -0.1700
Data Index: 5338836 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4995. Min Range: -6.4995
Max Act: 5.9058. Min Act: -0.1700
Data Index: 117464 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4995. Min Range: -6.4995
Max Act: 5.9058. Min Act: -0.1700
Data Index: 3299103 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4995. Min Range: -6.4995
Max Act: 5.8745. Min Act: -0.1700
Data Index: 6670755 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #19