Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1745 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5307. Min Range: -3.5307
Max Act: 3.5307. Min Act: -0.1700
Data Index: 839082 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5307. Min Range: -3.5307
Max Act: 3.0595. Min Act: -0.1700
Data Index: 5024180 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5307. Min Range: -3.5307
Max Act: 3.0280. Min Act: -0.1700
Data Index: 8156260 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5307. Min Range: -3.5307
Max Act: 2.9964. Min Act: -0.1700
Data Index: 4933003 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5307. Min Range: -3.5307
Max Act: 3.0122. Min Act: -0.1700
Data Index: 7456464 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5307. Min Range: -3.5307
Max Act: 2.9806. Min Act: -0.1700
Data Index: 6202703 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5307. Min Range: -3.5307
Max Act: 2.9806. Min Act: -0.1700
Data Index: 2441707 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5307. Min Range: -3.5307
Max Act: 2.9647. Min Act: -0.1700
Data Index: 4796 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5307. Min Range: -3.5307
Max Act: 2.9647. Min Act: -0.1700
Data Index: 3423392 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5307. Min Range: -3.5307
Max Act: 2.9489. Min Act: -0.1700
Data Index: 7696405 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5307. Min Range: -3.5307
Max Act: 2.9647. Min Act: -0.1700
Data Index: 4495961 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5307. Min Range: -3.5307
Max Act: 2.9489. Min Act: -0.1700
Data Index: 7280944 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5307. Min Range: -3.5307
Max Act: 2.9489. Min Act: -0.1700
Data Index: 7924154 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5307. Min Range: -3.5307
Max Act: 2.9489. Min Act: -0.1700
Data Index: 7125205 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5307. Min Range: -3.5307
Max Act: 2.9489. Min Act: -0.1700
Data Index: 2519056 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5307. Min Range: -3.5307
Max Act: 2.9331. Min Act: -0.1700
Data Index: 7898887 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5307. Min Range: -3.5307
Max Act: 2.9331. Min Act: -0.1700
Data Index: 6969857 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5307. Min Range: -3.5307
Max Act: 2.9331. Min Act: -0.1700
Data Index: 3217745 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5307. Min Range: -3.5307
Max Act: 2.9331. Min Act: -0.1700
Data Index: 5852824 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5307. Min Range: -3.5307
Max Act: 2.9172. Min Act: -0.1700
Data Index: 7898882 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #19