Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3977 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.5571. Min Range: -2.5571
Max Act: 2.5571. Min Act: -0.1700
Data Index: 756438 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5571. Min Range: -2.5571
Max Act: 2.4924. Min Act: -0.1700
Data Index: 3605422 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5571. Min Range: -2.5571
Max Act: 2.3621. Min Act: -0.1700
Data Index: 4981318 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5571. Min Range: -2.5571
Max Act: 2.3293. Min Act: -0.1700
Data Index: 5981880 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5571. Min Range: -2.5571
Max Act: 2.3457. Min Act: -0.1700
Data Index: 806560 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5571. Min Range: -2.5571
Max Act: 2.3293. Min Act: -0.1700
Data Index: 8646729 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5571. Min Range: -2.5571
Max Act: 2.3129. Min Act: -0.1700
Data Index: 4367549 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5571. Min Range: -2.5571
Max Act: 2.2964. Min Act: -0.1700
Data Index: 4862496 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5571. Min Range: -2.5571
Max Act: 2.2799. Min Act: -0.1700
Data Index: 7208742 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5571. Min Range: -2.5571
Max Act: 2.2799. Min Act: -0.1700
Data Index: 2110208 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5571. Min Range: -2.5571
Max Act: 2.2799. Min Act: -0.1700
Data Index: 4479859 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5571. Min Range: -2.5571
Max Act: 2.2799. Min Act: -0.1700
Data Index: 2641201 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5571. Min Range: -2.5571
Max Act: 2.2635. Min Act: -0.1700
Data Index: 850168 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5571. Min Range: -2.5571
Max Act: 2.2799. Min Act: -0.1700
Data Index: 5287440 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5571. Min Range: -2.5571
Max Act: 2.2799. Min Act: -0.1700
Data Index: 5838638 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5571. Min Range: -2.5571
Max Act: 2.2635. Min Act: -0.1700
Data Index: 2348061 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5571. Min Range: -2.5571
Max Act: 2.2635. Min Act: -0.1700
Data Index: 4470457 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5571. Min Range: -2.5571
Max Act: 2.2635. Min Act: -0.1700
Data Index: 6320921 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5571. Min Range: -2.5571
Max Act: 2.2635. Min Act: -0.1700
Data Index: 7613293 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5571. Min Range: -2.5571
Max Act: 2.2635. Min Act: -0.1700
Data Index: 5366839 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #19