Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1946 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3275. Min Range: -6.3275
Max Act: 6.3275. Min Act: -0.1700
Data Index: 4798202 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3275. Min Range: -6.3275
Max Act: 6.2337. Min Act: -0.1700
Data Index: 4113161 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3275. Min Range: -6.3275
Max Act: 6.1400. Min Act: -0.1700
Data Index: 2196935 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3275. Min Range: -6.3275
Max Act: 6.1087. Min Act: -0.1700
Data Index: 3664478 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3275. Min Range: -6.3275
Max Act: 6.1087. Min Act: -0.1700
Data Index: 8137441 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3275. Min Range: -6.3275
Max Act: 6.0462. Min Act: -0.1700
Data Index: 6103932 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3275. Min Range: -6.3275
Max Act: 6.0150. Min Act: -0.1700
Data Index: 7263331 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3275. Min Range: -6.3275
Max Act: 6.0150. Min Act: -0.1700
Data Index: 5692780 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3275. Min Range: -6.3275
Max Act: 5.9837. Min Act: -0.1700
Data Index: 7906126 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3275. Min Range: -6.3275
Max Act: 5.9837. Min Act: -0.1700
Data Index: 5343481 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3275. Min Range: -6.3275
Max Act: 5.9837. Min Act: -0.1700
Data Index: 7933723 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3275. Min Range: -6.3275
Max Act: 5.9837. Min Act: -0.1700
Data Index: 1713135 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3275. Min Range: -6.3275
Max Act: 5.8900. Min Act: -0.1700
Data Index: 4138878 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3275. Min Range: -6.3275
Max Act: 5.9212. Min Act: -0.1700
Data Index: 565681 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3275. Min Range: -6.3275
Max Act: 5.9212. Min Act: -0.1700
Data Index: 4241854 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3275. Min Range: -6.3275
Max Act: 5.8900. Min Act: -0.1700
Data Index: 6757206 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3275. Min Range: -6.3275
Max Act: 5.8900. Min Act: -0.1700
Data Index: 3033811 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3275. Min Range: -6.3275
Max Act: 5.8900. Min Act: -0.1700
Data Index: 2188881 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3275. Min Range: -6.3275
Max Act: 5.8900. Min Act: -0.1700
Data Index: 7314548 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3275. Min Range: -6.3275
Max Act: 5.8900. Min Act: -0.1700
Data Index: 4225129 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #19