Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2741 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3650. Min Range: -7.3650
Max Act: 7.3650. Min Act: -0.1700
Data Index: 1482124 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3650. Min Range: -7.3650
Max Act: 7.3025. Min Act: -0.1700
Data Index: 8334213 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3650. Min Range: -7.3650
Max Act: 7.3025. Min Act: -0.1700
Data Index: 325543 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3650. Min Range: -7.3650
Max Act: 7.2400. Min Act: -0.1700
Data Index: 7273063 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3650. Min Range: -7.3650
Max Act: 7.2400. Min Act: -0.1700
Data Index: 6787809 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3650. Min Range: -7.3650
Max Act: 7.2088. Min Act: -0.1700
Data Index: 587488 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3650. Min Range: -7.3650
Max Act: 7.2088. Min Act: -0.1700
Data Index: 4245964 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3650. Min Range: -7.3650
Max Act: 7.2088. Min Act: -0.1700
Data Index: 1530704 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3650. Min Range: -7.3650
Max Act: 7.2088. Min Act: -0.1700
Data Index: 6571294 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3650. Min Range: -7.3650
Max Act: 7.2400. Min Act: -0.1700
Data Index: 6553049 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3650. Min Range: -7.3650
Max Act: 7.2088. Min Act: -0.1700
Data Index: 2354996 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3650. Min Range: -7.3650
Max Act: 7.1775. Min Act: -0.1700
Data Index: 6180188 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3650. Min Range: -7.3650
Max Act: 7.1775. Min Act: -0.1700
Data Index: 4947886 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3650. Min Range: -7.3650
Max Act: 7.1775. Min Act: -0.1700
Data Index: 8220201 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3650. Min Range: -7.3650
Max Act: 7.2088. Min Act: -0.1700
Data Index: 1271906 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3650. Min Range: -7.3650
Max Act: 7.1463. Min Act: -0.1700
Data Index: 7820083 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3650. Min Range: -7.3650
Max Act: 7.1463. Min Act: -0.1700
Data Index: 8142784 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3650. Min Range: -7.3650
Max Act: 7.1150. Min Act: -0.1700
Data Index: 3700020 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3650. Min Range: -7.3650
Max Act: 7.1463. Min Act: -0.1700
Data Index: 4630405 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3650. Min Range: -7.3650
Max Act: 7.1463. Min Act: -0.1700
Data Index: 1824750 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #19