Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3095 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0318. Min Range: -10.0318
Max Act: 10.0318. Min Act: -0.1700
Data Index: 3015546 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0318. Min Range: -10.0318
Max Act: 9.8443. Min Act: -0.1700
Data Index: 1562746 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0318. Min Range: -10.0318
Max Act: 9.8443. Min Act: -0.1700
Data Index: 5368059 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0318. Min Range: -10.0318
Max Act: 9.8443. Min Act: -0.1700
Data Index: 6087903 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0318. Min Range: -10.0318
Max Act: 9.5943. Min Act: -0.1700
Data Index: 117712 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0318. Min Range: -10.0318
Max Act: 9.5318. Min Act: -0.1700
Data Index: 615214 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0318. Min Range: -10.0318
Max Act: 9.5318. Min Act: -0.1700
Data Index: 3687970 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0318. Min Range: -10.0318
Max Act: 9.4693. Min Act: -0.1700
Data Index: 5856056 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0318. Min Range: -10.0318
Max Act: 9.4068. Min Act: -0.1700
Data Index: 8279567 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0318. Min Range: -10.0318
Max Act: 9.3443. Min Act: -0.1700
Data Index: 6873119 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0318. Min Range: -10.0318
Max Act: 9.4068. Min Act: -0.1700
Data Index: 7664637 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0318. Min Range: -10.0318
Max Act: 9.3443. Min Act: -0.1700
Data Index: 3876429 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0318. Min Range: -10.0318
Max Act: 9.3443. Min Act: -0.1700
Data Index: 6391583 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0318. Min Range: -10.0318
Max Act: 9.3443. Min Act: -0.1700
Data Index: 4201236 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0318. Min Range: -10.0318
Max Act: 9.2818. Min Act: -0.1700
Data Index: 3802559 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0318. Min Range: -10.0318
Max Act: 9.2818. Min Act: -0.1700
Data Index: 4096422 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0318. Min Range: -10.0318
Max Act: 9.2818. Min Act: -0.1700
Data Index: 3849258 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0318. Min Range: -10.0318
Max Act: 9.2193. Min Act: -0.1700
Data Index: 1382675 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0318. Min Range: -10.0318
Max Act: 9.1568. Min Act: -0.1700
Data Index: 7423095 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0318. Min Range: -10.0318
Max Act: 9.1568. Min Act: -0.1700
Data Index: 4027098 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #19