Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3875 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.3692. Min Range: -9.3692
Max Act: 9.3692. Min Act: -0.1700
Data Index: 6007940 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3692. Min Range: -9.3692
Max Act: 9.3067. Min Act: -0.1700
Data Index: 2131637 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3692. Min Range: -9.3692
Max Act: 9.2442. Min Act: -0.1700
Data Index: 4249078 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3692. Min Range: -9.3692
Max Act: 9.1817. Min Act: -0.1700
Data Index: 1039347 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3692. Min Range: -9.3692
Max Act: 9.2442. Min Act: -0.1700
Data Index: 3206569 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3692. Min Range: -9.3692
Max Act: 9.1192. Min Act: -0.1700
Data Index: 5754908 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3692. Min Range: -9.3692
Max Act: 9.1192. Min Act: -0.1700
Data Index: 6021477 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3692. Min Range: -9.3692
Max Act: 9.1192. Min Act: -0.1700
Data Index: 7715246 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3692. Min Range: -9.3692
Max Act: 9.1192. Min Act: -0.1700
Data Index: 3330912 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3692. Min Range: -9.3692
Max Act: 8.9942. Min Act: -0.1700
Data Index: 3841258 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3692. Min Range: -9.3692
Max Act: 8.9942. Min Act: -0.1700
Data Index: 6274417 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3692. Min Range: -9.3692
Max Act: 8.9942. Min Act: -0.1700
Data Index: 3405020 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3692. Min Range: -9.3692
Max Act: 8.9317. Min Act: -0.1700
Data Index: 8480622 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3692. Min Range: -9.3692
Max Act: 8.9942. Min Act: -0.1700
Data Index: 5080377 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3692. Min Range: -9.3692
Max Act: 8.9317. Min Act: -0.1700
Data Index: 1311020 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3692. Min Range: -9.3692
Max Act: 8.9317. Min Act: -0.1700
Data Index: 1271871 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3692. Min Range: -9.3692
Max Act: 8.9317. Min Act: -0.1700
Data Index: 831266 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3692. Min Range: -9.3692
Max Act: 8.9317. Min Act: -0.1700
Data Index: 6240103 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3692. Min Range: -9.3692
Max Act: 8.9317. Min Act: -0.1700
Data Index: 5701610 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3692. Min Range: -9.3692
Max Act: 8.8692. Min Act: -0.1700
Data Index: 2371042 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #19