Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2579 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 10.3646. Min Range: -10.3646
Max Act: 10.3646. Min Act: -0.1700
Data Index: 1345618 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3646. Min Range: -10.3646
Max Act: 10.0521. Min Act: -0.1700
Data Index: 5758142 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3646. Min Range: -10.3646
Max Act: 10.0521. Min Act: -0.1700
Data Index: 8568884 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3646. Min Range: -10.3646
Max Act: 10.0521. Min Act: -0.1700
Data Index: 108494 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3646. Min Range: -10.3646
Max Act: 9.9896. Min Act: -0.1700
Data Index: 8466275 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3646. Min Range: -10.3646
Max Act: 9.7396. Min Act: -0.1700
Data Index: 5018 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3646. Min Range: -10.3646
Max Act: 9.7396. Min Act: -0.1700
Data Index: 4011101 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3646. Min Range: -10.3646
Max Act: 9.6771. Min Act: -0.1700
Data Index: 7453655 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3646. Min Range: -10.3646
Max Act: 9.6146. Min Act: -0.1700
Data Index: 6246739 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3646. Min Range: -10.3646
Max Act: 9.5521. Min Act: -0.1700
Data Index: 6115224 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3646. Min Range: -10.3646
Max Act: 9.5521. Min Act: -0.1700
Data Index: 1285096 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3646. Min Range: -10.3646
Max Act: 9.4896. Min Act: -0.1700
Data Index: 3907942 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3646. Min Range: -10.3646
Max Act: 9.4896. Min Act: -0.1700
Data Index: 1424728 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3646. Min Range: -10.3646
Max Act: 9.4896. Min Act: -0.1700
Data Index: 7474105 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3646. Min Range: -10.3646
Max Act: 9.4896. Min Act: -0.1700
Data Index: 993036 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3646. Min Range: -10.3646
Max Act: 9.4896. Min Act: -0.1700
Data Index: 3739989 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3646. Min Range: -10.3646
Max Act: 9.4271. Min Act: -0.1700
Data Index: 6046753 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3646. Min Range: -10.3646
Max Act: 9.3646. Min Act: -0.1700
Data Index: 7215233 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3646. Min Range: -10.3646
Max Act: 9.3646. Min Act: -0.1700
Data Index: 2342193 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3646. Min Range: -10.3646
Max Act: 9.3646. Min Act: -0.1700
Data Index: 629310 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #19