Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3210 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9852. Min Range: -3.9852
Max Act: 3.9852. Min Act: -0.1700
Data Index: 3262644 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9852. Min Range: -3.9852
Max Act: 3.9539. Min Act: -0.1700
Data Index: 4440772 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9852. Min Range: -3.9852
Max Act: 3.9539. Min Act: -0.1700
Data Index: 1832118 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9852. Min Range: -3.9852
Max Act: 3.8601. Min Act: -0.1700
Data Index: 361495 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9852. Min Range: -3.9852
Max Act: 3.8288. Min Act: -0.1700
Data Index: 8669738 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9852. Min Range: -3.9852
Max Act: 3.8288. Min Act: -0.1700
Data Index: 3968851 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9852. Min Range: -3.9852
Max Act: 3.7976. Min Act: -0.1700
Data Index: 1931913 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9852. Min Range: -3.9852
Max Act: 3.7976. Min Act: -0.1700
Data Index: 4586745 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9852. Min Range: -3.9852
Max Act: 3.7976. Min Act: -0.1700
Data Index: 3444062 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9852. Min Range: -3.9852
Max Act: 3.7663. Min Act: -0.1700
Data Index: 5051951 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9852. Min Range: -3.9852
Max Act: 3.7663. Min Act: -0.1700
Data Index: 7464341 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9852. Min Range: -3.9852
Max Act: 3.7350. Min Act: -0.1700
Data Index: 6416726 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9852. Min Range: -3.9852
Max Act: 3.7350. Min Act: -0.1700
Data Index: 4689004 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9852. Min Range: -3.9852
Max Act: 3.7037. Min Act: -0.1700
Data Index: 6620439 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9852. Min Range: -3.9852
Max Act: 3.7350. Min Act: -0.1700
Data Index: 7198275 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9852. Min Range: -3.9852
Max Act: 3.7037. Min Act: -0.1700
Data Index: 5897875 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9852. Min Range: -3.9852
Max Act: 3.6724. Min Act: -0.1700
Data Index: 5261248 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9852. Min Range: -3.9852
Max Act: 3.7037. Min Act: -0.1700
Data Index: 5124768 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9852. Min Range: -3.9852
Max Act: 3.7037. Min Act: -0.1700
Data Index: 3118253 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9852. Min Range: -3.9852
Max Act: 3.6724. Min Act: -0.1700
Data Index: 7498417 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #19