Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2050 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9069. Min Range: -3.9069
Max Act: 3.8912. Min Act: -0.1700
Data Index: 5618161 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9069. Min Range: -3.9069
Max Act: 3.9069. Min Act: -0.1700
Data Index: 7204983 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9069. Min Range: -3.9069
Max Act: 3.8443. Min Act: -0.1700
Data Index: 184063 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9069. Min Range: -3.9069
Max Act: 3.8756. Min Act: -0.1700
Data Index: 985232 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9069. Min Range: -3.9069
Max Act: 3.8443. Min Act: -0.1700
Data Index: 1618535 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9069. Min Range: -3.9069
Max Act: 3.8600. Min Act: -0.1700
Data Index: 2215027 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9069. Min Range: -3.9069
Max Act: 3.8443. Min Act: -0.1700
Data Index: 1159997 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9069. Min Range: -3.9069
Max Act: 3.8600. Min Act: -0.1700
Data Index: 7766267 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9069. Min Range: -3.9069
Max Act: 3.7974. Min Act: -0.1700
Data Index: 1668600 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9069. Min Range: -3.9069
Max Act: 3.8287. Min Act: -0.1700
Data Index: 882934 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9069. Min Range: -3.9069
Max Act: 3.7974. Min Act: -0.1700
Data Index: 2393582 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9069. Min Range: -3.9069
Max Act: 3.7974. Min Act: -0.1700
Data Index: 4834383 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9069. Min Range: -3.9069
Max Act: 3.7974. Min Act: -0.1700
Data Index: 1908436 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9069. Min Range: -3.9069
Max Act: 3.7974. Min Act: -0.1700
Data Index: 2240328 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9069. Min Range: -3.9069
Max Act: 3.7349. Min Act: -0.1700
Data Index: 8589111 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9069. Min Range: -3.9069
Max Act: 3.7349. Min Act: -0.1700
Data Index: 8047841 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9069. Min Range: -3.9069
Max Act: 3.7192. Min Act: -0.1700
Data Index: 2824644 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9069. Min Range: -3.9069
Max Act: 3.7661. Min Act: -0.1700
Data Index: 5780174 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9069. Min Range: -3.9069
Max Act: 3.7349. Min Act: -0.1700
Data Index: 8571487 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9069. Min Range: -3.9069
Max Act: 3.7192. Min Act: -0.1700
Data Index: 7042218 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #19