Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2570 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8685. Min Range: -5.8685
Max Act: 5.8685. Min Act: -0.1700
Data Index: 6576428 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8685. Min Range: -5.8685
Max Act: 5.7123. Min Act: -0.1700
Data Index: 801517 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8685. Min Range: -5.8685
Max Act: 5.6498. Min Act: -0.1700
Data Index: 4148258 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8685. Min Range: -5.8685
Max Act: 5.6498. Min Act: -0.1700
Data Index: 4710487 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8685. Min Range: -5.8685
Max Act: 5.5248. Min Act: -0.1700
Data Index: 4331057 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8685. Min Range: -5.8685
Max Act: 5.4623. Min Act: -0.1700
Data Index: 7125234 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8685. Min Range: -5.8685
Max Act: 5.3998. Min Act: -0.1700
Data Index: 1600799 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8685. Min Range: -5.8685
Max Act: 5.4310. Min Act: -0.1700
Data Index: 927958 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8685. Min Range: -5.8685
Max Act: 5.3685. Min Act: -0.1700
Data Index: 1101762 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8685. Min Range: -5.8685
Max Act: 5.3373. Min Act: -0.1700
Data Index: 3228338 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8685. Min Range: -5.8685
Max Act: 5.3373. Min Act: -0.1700
Data Index: 7208317 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8685. Min Range: -5.8685
Max Act: 5.3060. Min Act: -0.1700
Data Index: 8272293 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8685. Min Range: -5.8685
Max Act: 5.3060. Min Act: -0.1700
Data Index: 4949691 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8685. Min Range: -5.8685
Max Act: 5.3060. Min Act: -0.1700
Data Index: 6974118 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8685. Min Range: -5.8685
Max Act: 5.3060. Min Act: -0.1700
Data Index: 4337928 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8685. Min Range: -5.8685
Max Act: 5.2435. Min Act: -0.1700
Data Index: 3868094 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8685. Min Range: -5.8685
Max Act: 5.2435. Min Act: -0.1700
Data Index: 3517670 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8685. Min Range: -5.8685
Max Act: 5.2435. Min Act: -0.1700
Data Index: 5866073 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8685. Min Range: -5.8685
Max Act: 5.2435. Min Act: -0.1700
Data Index: 3394266 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8685. Min Range: -5.8685
Max Act: 5.2435. Min Act: -0.1700
Data Index: 7835338 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #19