Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5100 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2239. Min Range: -6.2239
Max Act: 6.2239. Min Act: -0.1700
Data Index: 6689918 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2239. Min Range: -6.2239
Max Act: 6.0364. Min Act: -0.1700
Data Index: 3862000 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2239. Min Range: -6.2239
Max Act: 6.0364. Min Act: -0.1700
Data Index: 4636891 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2239. Min Range: -6.2239
Max Act: 5.9427. Min Act: -0.1700
Data Index: 5511514 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2239. Min Range: -6.2239
Max Act: 5.9114. Min Act: -0.1700
Data Index: 8185865 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2239. Min Range: -6.2239
Max Act: 5.9114. Min Act: -0.1700
Data Index: 4103758 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2239. Min Range: -6.2239
Max Act: 5.8802. Min Act: -0.1700
Data Index: 5021929 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2239. Min Range: -6.2239
Max Act: 5.8802. Min Act: -0.1700
Data Index: 4114417 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2239. Min Range: -6.2239
Max Act: 5.8489. Min Act: -0.1700
Data Index: 6368110 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2239. Min Range: -6.2239
Max Act: 5.8802. Min Act: -0.1700
Data Index: 4588377 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2239. Min Range: -6.2239
Max Act: 5.8489. Min Act: -0.1700
Data Index: 3097803 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2239. Min Range: -6.2239
Max Act: 5.8489. Min Act: -0.1700
Data Index: 5177856 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2239. Min Range: -6.2239
Max Act: 5.8177. Min Act: -0.1700
Data Index: 2923262 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2239. Min Range: -6.2239
Max Act: 5.8177. Min Act: -0.1700
Data Index: 8210864 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2239. Min Range: -6.2239
Max Act: 5.7864. Min Act: -0.1700
Data Index: 4744412 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2239. Min Range: -6.2239
Max Act: 5.7552. Min Act: -0.1700
Data Index: 3205019 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2239. Min Range: -6.2239
Max Act: 5.7552. Min Act: -0.1700
Data Index: 2217974 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2239. Min Range: -6.2239
Max Act: 5.7552. Min Act: -0.1700
Data Index: 736887 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2239. Min Range: -6.2239
Max Act: 5.6927. Min Act: -0.1700
Data Index: 1727911 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2239. Min Range: -6.2239
Max Act: 5.7239. Min Act: -0.1700
Data Index: 3629957 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #19