Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2465 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0330. Min Range: -8.0330
Max Act: 8.0330. Min Act: -0.1700
Data Index: 4346671 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0330. Min Range: -8.0330
Max Act: 7.9080. Min Act: -0.1700
Data Index: 3485942 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0330. Min Range: -8.0330
Max Act: 7.8142. Min Act: -0.1700
Data Index: 7675150 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0330. Min Range: -8.0330
Max Act: 7.7517. Min Act: -0.1700
Data Index: 4485127 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0330. Min Range: -8.0330
Max Act: 7.6267. Min Act: -0.1700
Data Index: 2411654 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0330. Min Range: -8.0330
Max Act: 7.6267. Min Act: -0.1700
Data Index: 3671065 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0330. Min Range: -8.0330
Max Act: 7.5955. Min Act: -0.1700
Data Index: 7331316 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0330. Min Range: -8.0330
Max Act: 7.5955. Min Act: -0.1700
Data Index: 6606394 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0330. Min Range: -8.0330
Max Act: 7.5330. Min Act: -0.1700
Data Index: 7115802 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0330. Min Range: -8.0330
Max Act: 7.5330. Min Act: -0.1700
Data Index: 2687647 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0330. Min Range: -8.0330
Max Act: 7.5330. Min Act: -0.1700
Data Index: 5918306 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0330. Min Range: -8.0330
Max Act: 7.5330. Min Act: -0.1700
Data Index: 3547295 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0330. Min Range: -8.0330
Max Act: 7.5017. Min Act: -0.1700
Data Index: 44522 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0330. Min Range: -8.0330
Max Act: 7.4705. Min Act: -0.1700
Data Index: 3657053 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0330. Min Range: -8.0330
Max Act: 7.4080. Min Act: -0.1700
Data Index: 6203764 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0330. Min Range: -8.0330
Max Act: 7.3767. Min Act: -0.1700
Data Index: 5801397 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0330. Min Range: -8.0330
Max Act: 7.4080. Min Act: -0.1700
Data Index: 2548810 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0330. Min Range: -8.0330
Max Act: 7.3767. Min Act: -0.1700
Data Index: 3324139 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0330. Min Range: -8.0330
Max Act: 7.3767. Min Act: -0.1700
Data Index: 6537164 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0330. Min Range: -8.0330
Max Act: 7.3455. Min Act: -0.1700
Data Index: 7021770 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #19