Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2251 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4195. Min Range: -5.4195
Max Act: 5.3882. Min Act: -0.1700
Data Index: 1867023 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4195. Min Range: -5.4195
Max Act: 5.4195. Min Act: -0.1700
Data Index: 5083606 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4195. Min Range: -5.4195
Max Act: 5.3257. Min Act: -0.1700
Data Index: 4624277 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4195. Min Range: -5.4195
Max Act: 5.2320. Min Act: -0.1700
Data Index: 6211376 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4195. Min Range: -5.4195
Max Act: 5.1695. Min Act: -0.1700
Data Index: 7776413 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4195. Min Range: -5.4195
Max Act: 5.1695. Min Act: -0.1700
Data Index: 1761628 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4195. Min Range: -5.4195
Max Act: 5.1070. Min Act: -0.1700
Data Index: 7331312 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4195. Min Range: -5.4195
Max Act: 5.1382. Min Act: -0.1700
Data Index: 1382839 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4195. Min Range: -5.4195
Max Act: 5.1695. Min Act: -0.1700
Data Index: 7237067 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4195. Min Range: -5.4195
Max Act: 5.1070. Min Act: -0.1700
Data Index: 951062 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4195. Min Range: -5.4195
Max Act: 5.0757. Min Act: -0.1700
Data Index: 4217550 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4195. Min Range: -5.4195
Max Act: 5.0757. Min Act: -0.1700
Data Index: 3292361 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4195. Min Range: -5.4195
Max Act: 5.0132. Min Act: -0.1700
Data Index: 1876993 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4195. Min Range: -5.4195
Max Act: 5.0757. Min Act: -0.1700
Data Index: 8613530 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4195. Min Range: -5.4195
Max Act: 5.0445. Min Act: -0.1700
Data Index: 7900740 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4195. Min Range: -5.4195
Max Act: 4.9820. Min Act: -0.1700
Data Index: 6170939 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4195. Min Range: -5.4195
Max Act: 5.0132. Min Act: -0.1700
Data Index: 1505631 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4195. Min Range: -5.4195
Max Act: 5.0445. Min Act: -0.1700
Data Index: 1893278 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4195. Min Range: -5.4195
Max Act: 5.0132. Min Act: -0.1700
Data Index: 2263557 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4195. Min Range: -5.4195
Max Act: 4.9820. Min Act: -0.1700
Data Index: 4253983 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #19