Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2346 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6136. Min Range: -4.6136
Max Act: 4.6136. Min Act: -0.1700
Data Index: 6027076 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6136. Min Range: -4.6136
Max Act: 4.4886. Min Act: -0.1700
Data Index: 1760579 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6136. Min Range: -4.6136
Max Act: 4.4886. Min Act: -0.1700
Data Index: 6667971 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6136. Min Range: -4.6136
Max Act: 4.4574. Min Act: -0.1700
Data Index: 7059921 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6136. Min Range: -4.6136
Max Act: 4.4261. Min Act: -0.1700
Data Index: 249985 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6136. Min Range: -4.6136
Max Act: 4.4261. Min Act: -0.1700
Data Index: 6709334 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6136. Min Range: -4.6136
Max Act: 4.4261. Min Act: -0.1700
Data Index: 801626 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6136. Min Range: -4.6136
Max Act: 4.4261. Min Act: -0.1700
Data Index: 6368018 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6136. Min Range: -4.6136
Max Act: 4.3636. Min Act: -0.1700
Data Index: 969814 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6136. Min Range: -4.6136
Max Act: 4.4261. Min Act: -0.1700
Data Index: 1621051 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6136. Min Range: -4.6136
Max Act: 4.3636. Min Act: -0.1700
Data Index: 4171281 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6136. Min Range: -4.6136
Max Act: 4.3636. Min Act: -0.1700
Data Index: 4923436 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6136. Min Range: -4.6136
Max Act: 4.3636. Min Act: -0.1700
Data Index: 1075893 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6136. Min Range: -4.6136
Max Act: 4.3324. Min Act: -0.1700
Data Index: 6615754 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6136. Min Range: -4.6136
Max Act: 4.3324. Min Act: -0.1700
Data Index: 2361320 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6136. Min Range: -4.6136
Max Act: 4.3324. Min Act: -0.1700
Data Index: 7798730 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6136. Min Range: -4.6136
Max Act: 4.3011. Min Act: -0.1700
Data Index: 6316133 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6136. Min Range: -4.6136
Max Act: 4.3011. Min Act: -0.1700
Data Index: 7537746 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6136. Min Range: -4.6136
Max Act: 4.3011. Min Act: -0.1700
Data Index: 1603249 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6136. Min Range: -4.6136
Max Act: 4.3011. Min Act: -0.1700
Data Index: 2753630 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #19